Awesome MCP Servers by AI Anytime

Directory / Cloud, ops & data

CorpusIQ

Read-only MCP access to live business data across 40+ systems, including Stripe, QuickBooks, GA4, Shopify and HubSpot, with a source citation on each figure. Endpoint: https://mcp2.corpusiq.io/mcp

Live  Answered an MCP handshake without credentials and listed 121 tools.

Category
Cloud, ops & data
Transport
http
Source
https://github.com/CorpusIQ/corpusiq-docs
Endpoint
https://mcp2.corpusiq.io/mcp
MCP Registry
io.corpusiq/multi-source-mcp
Reports itself as
multi-source-mcp 1.0.0
Protocol
2025-03-26
Tools
121
Context cost
about 62,871 tokens for the tool definitions (estimated at four characters per token)
Tool definitions last changed
no change seen since first check
Handshake time
308 ms
Repository
29 stars · last push 2026-11-22
Last checked
2026-11-22 11:27:30 UTC
Listed since
2026-11-18

Health and compatibility

Endpoint reachableVerifiedResponded in 308 ms
MCP handshake (initialize)VerifiedCompleted without credentials
Tool discovery (tools/list)Verified121 tools listed
AuthenticationVerifiedNone needed to connect
Protocol versionVerified2025-03-26
TransportVerifiedStreamable HTTP
Capabilities declaredVerifiedprompts, resources, tools

Last checked . Verified means the check saw it happen; it says nothing about whether the server is safe.

Recent history

5 daily checks so far; median response 227 ms. Green answered, violet asked for auth, red did not answer.

Set up in your client

Claude Code

Run this in a terminal:

claude mcp add --transport http corpusiq https://mcp2.corpusiq.io/mcp

Claude Desktop

Open Settings → Connectors → Add custom connector and paste this URL:

https://mcp2.corpusiq.io/mcp

Or bridge it through mcp-remote in claude_desktop_config.json (needs Node.js):

{
  "mcpServers": {
    "corpusiq": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp2.corpusiq.io/mcp"
      ]
    }
  }
}

Cursor

Add to Cursor

Or add it to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):

{
  "mcpServers": {
    "corpusiq": {
      "url": "https://mcp2.corpusiq.io/mcp"
    }
  }
}

VS Code

Add to VS Code

Or add it to .vscode/mcp.json:

{
  "servers": {
    "corpusiq": {
      "type": "http",
      "url": "https://mcp2.corpusiq.io/mcp"
    }
  }
}

Or from a terminal:

code --add-mcp '{"name": "corpusiq", "type": "http", "url": "https://mcp2.corpusiq.io/mcp"}'

Windsurf

Add it to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "corpusiq": {
      "serverUrl": "https://mcp2.corpusiq.io/mcp"
    }
  }
}

Other clients

Most clients accept this shape. The endpoint is:

https://mcp2.corpusiq.io/mcp
{
  "mcpServers": {
    "corpusiq": {
      "type": "http",
      "url": "https://mcp2.corpusiq.io/mcp"
    }
  }
}

If it does not connect

Tools 121

Names, descriptions and input schemas exactly as the server returned them on 2026-11-22. This is the server author's own text. Nothing is run from this page. Labels such as read-only are declared by the server and are not verified. Raw JSON

activecampaign_connectorread-onlyexternal accessActiveCampaign email marketing and CRM: contacts, lists, campaigns, automations, deals, and tags. When the …

ActiveCampaign email marketing and CRM: contacts, lists, campaigns, automations, deals, and tags. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without a …

ParameterTypeDescription
actionstringrequiredget_contacts: List ActiveCampaign contacts with optional filters | get_campaigns: List ActiveCampaign campaigns with status and performance | get_automations: List ActiveCampaign automations | get_deals: List ActiveCampaign deals/pipeline opportunities | … One of: get_contacts, get_campaigns, get_automations, get_deals, get_account_info, get_contact, search_contacts, get_lists …
paramsobjectoptionalAction-specific parameters. get_contacts: {limit?: integer, offset?: integer, query?: string} | get_campaigns: {limit?: integer, offset?: integer} | get_automations: {limit?: integer} | get_deals: {limit?: integer} | get_account_info: none | get_contact: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "activecampaign_connector",
    "arguments": {
      "action": "get_contacts"
    }
  }
}
add_my_youtube_brand_channelcan modifydestructiveexternal accessRegister a YouTube Brand Account channel for the authenticated user. Resolves the brand's channel_id from the …

Register a YouTube Brand Account channel for the authenticated user. Resolves the brand's channel_id from the @handle, persists the registration, and immediately surfaces the brand in list_my_youtube_channels with source='user-registered'. When set_as_primary=true (or when no prior brand is registered), per-channel my_youtube_* tools default to this brand when no channel_id is supplied. Use after get_youtube_channel(handle='@Brand') confirms the channel exists. When tool output supplies an …

ParameterTypeDescription
handlestringrequiredYouTube @handle of the Brand Account channel (e.g. '@FourPeaksTactical')
labelstringoptionalOptional human-readable label; defaults to the channel's YouTube title
set_as_primarybooleanoptionalWhen true, mark this brand as the user's primary so per-channel tools default to it. First brand registered is auto-primary regardless.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "add_my_youtube_brand_channel",
    "arguments": {
      "handle": "..."
    }
  }
}
ahrefs_connectorread-onlyexternal accessAhrefs SEO platform: domain rating, backlink analysis, organic keywords, referring domains, competitor …

Ahrefs SEO platform: domain rating, backlink analysis, organic keywords, referring domains, competitor research, top pages by traffic, and keyword research. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so …

ParameterTypeDescription
actionstringrequiredget_domain_overview: Get a combined domain authority, backlink, and organic traffic overview from Ahrefs for a given domain. Returns Domain R | get_organic_keywords: Get the top organic (SEO) keywords that a domain ranks for in Ahrefs. Returns keyword, … One of: get_domain_overview, get_organic_keywords, get_backlinks_overview, get_refdomains, get_competitors, get_top_pages, get_keyword_overview
paramsobjectoptionalAction-specific parameters. get_domain_overview: {domain: string} | get_organic_keywords: {domain: string, country?: string, limit?: integer} | get_backlinks_overview: {domain: string} | get_refdomains: {domain: string, limit?: integer} | get_competitors: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "ahrefs_connector",
    "arguments": {
      "action": "get_domain_overview"
    }
  }
}
ahrefs_dashboardread-onlyexternal accessFetch live Ahrefs domain overview, top organic keywords, and top pages and return a source-verified, …

Fetch live Ahrefs domain overview, top organic keywords, and top pages and return a source-verified, non-authoritative estimate dashboard with explicit top-N coverage and integrity receipts. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. …

ParameterTypeDescription
domainstringrequired
countrystringoptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "ahrefs_dashboard",
    "arguments": {
      "domain": "..."
    }
  }
}
airtable_connectorread-onlyexternal accessAirtable bases, tables, and records: browse, search, and retrieve structured data from Airtable databases. …

Airtable bases, tables, and records: browse, search, and retrieve structured data from Airtable databases. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. …

ParameterTypeDescription
actionstringrequiredlist_bases: List all Airtable bases the authenticated user has access to | list_tables: List all tables in a specific Airtable base | list_records: List records from an Airtable table with optional filtering, sorting, and pagination | search_records: Search … One of: list_bases, list_tables, list_records, search_records, get_record
paramsobjectoptionalAction-specific parameters. list_bases: none | list_tables: {base_id: string} | list_records: {base_id: string, table_id: string, page_size?: integer, offset?: string, fields?: array, filter_formula?: string, view?: string, projection?: object} | …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "airtable_connector",
    "arguments": {
      "action": "list_bases"
    }
  }
}
amazon_seller_connectorread-onlyexternal accessAmazon Seller Central data: orders, inventory, sales metrics, and seller account performance. When the user …

Amazon Seller Central data: orders, inventory, sales metrics, and seller account performance. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without a valid …

ParameterTypeDescription
actionstringrequiredlist_amazon_orders: List orders from the seller's Amazon store with optional date and status filters. Returns order summaries with order ID, | get_amazon_order: Get full details for a single Amazon order by order ID: shipping address, buyer info, payment … One of: list_amazon_orders, get_amazon_order, get_amazon_order_items, get_amazon_sales_metrics, list_amazon_inventory, list_amazon_listings, get_amazon_catalog_item, get_amazon_finances …
paramsobjectoptionalAction-specific parameters. list_amazon_orders: {created_after?: string, created_before?: string, order_statuses?: array, fulfillment_channels?: array, max_results?: integer, next_token?: string} | get_amazon_order: {order_id: string} | …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "amazon_seller_connector",
    "arguments": {
      "action": "list_amazon_orders"
    }
  }
}
ask_corpusiqread-onlyexternal accessAnswer a business question through CorpusIQ's deterministic server-side runbook executor. In router_first …

Answer a business question through CorpusIQ's deterministic server-side runbook executor. In router_first mode, CorpusIQ selects and pins the best matching runbook before validating connectors and executing its fixed read-only tool allowlist. In required_runbook mode, the caller pins an explicit runbook id. Returns the answer, source evidence, warnings, and a verifiable execution receipt; unsupported runbooks and missing prerequisites fail closed. A presentation runbook such as a dashboard or …

ParameterTypeDescription
questionstringrequiredThe user's plain-language business question.
modestringoptionalrouter_first asks the canonical skills router to select the runbook. required_runbook executes the supplied runbook_id without re-routing. One of: router_first, required_runbook
runbook_idstringoptionalRequired only when mode=required_runbook. Omit in router_first mode.
versionstringoptionalExact governed runbook version. Required with content_hash when mode=required_runbook.
content_hashstringoptionalExact governed runbook SHA-256 content hash. Required with version when mode=required_runbook.
argumentsobjectoptionalOptional explicit runbook arguments, such as start_date and end_date in YYYY-MM-DD form.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "ask_corpusiq",
    "arguments": {
      "question": "..."
    }
  }
}
axonaut_connectorread-onlyexternal accessAxonaut French all-in-one business management (CRM + invoicing + accounting): companies (third parties), …

Axonaut French all-in-one business management (CRM + invoicing + accounting): companies (third parties), quotations, invoices, opportunities (CRM pipeline), expenses, payments, suppliers, products, contracts, employees, and custom fields. Read-only via personal userApiKey (Path A). Cross-connector join keys: email, siret (French business registration number), company_name, invoice_id, currency — enabling Axonaut invoices ↔ Stripe charges (EUR revenue reconciliation) and Axonaut companies ↔ …

ParameterTypeDescription
actionstringrequiredget_account: Get the connected Axonaut account and authenticated user profile. Returns the user id, email, full_name, roles, and a ne | list_companies: List Axonaut companies (third parties: customers, prospects, and suppliers) one page at a time. Each … One of: get_account, list_companies, get_company, list_quotations, get_quotation, list_invoices, get_invoice, list_opportunities …
paramsobjectoptionalAction-specific parameters. get_account: none | list_companies: {page?: integer, page_size?: integer, search?: string, is_customer?: boolean, is_prospect?: boolean} | get_company: {companyId: string} | list_quotations: {page?: integer, page_size?: integer, …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "axonaut_connector",
    "arguments": {
      "action": "get_account"
    }
  }
}
axonaut_dashboardread-onlyexternal accessFetch live Axonaut invoices, payments, opportunities, and account data and return an evidence-backed CorpusIQ …

Fetch live Axonaut invoices, payments, opportunities, and account data and return an evidence-backed CorpusIQ PNG dashboard plus complete accessible text, structured business facts, reconciliation status, and an integrity receipt. Calculations are date-bounded and currency-safe. Inputs: optional start_date and end_date (default 30daysAgo/today; maximum 366 days). When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query …

ParameterTypeDescription
start_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
end_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "axonaut_dashboard",
    "arguments": {}
  }
}
bing_webmaster_connectorread-onlyexternal accessBing Webmaster Tools (Microsoft) organic-search data for a verified site: rank & traffic stats …

Bing Webmaster Tools (Microsoft) organic-search data for a verified site: rank & traffic stats (impressions/clicks over time), top search queries with positions, per-URL index & traffic detail, crawl statistics (crawled pages, in-index, errors, status codes), and inbound link counts. Use for Bing SEO reporting, organic-search visibility, keyword/query analysis, crawl health, and backlink volume. Auth: OAuth 2.0. When the user asks for a visual, trend, comparison, or recap, call chart_render …

ParameterTypeDescription
actionstringrequiredget_sites: List the sites the connected Bing Webmaster user has verified. Call this first to discover the siteUrl values the other | get_rank_and_traffic: Get the Bing organic rank & traffic time series for a verified site: daily impressions and clicks, plus … One of: get_sites, get_rank_and_traffic, get_query_stats, get_url_traffic, get_crawl_stats, get_link_counts
paramsobjectoptionalAction-specific parameters. get_sites: none | get_rank_and_traffic: {site_url: string} | get_query_stats: {site_url: string} | get_url_traffic: {site_url: string, url: string} | get_crawl_stats: {site_url: string} | get_link_counts: {site_url: string, page?: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "bing_webmaster_connector",
    "arguments": {
      "action": "get_sites"
    }
  }
}
bing_webmaster_dashboardread-onlyexternal accessFetch Bing-reported impressions, clicks, and top queries for an exact verified site, then return an …

Fetch Bing-reported impressions, clicks, and top queries for an exact verified site, then return an authoritative PNG dashboard with daily reconciliation, explicit top-query coverage, and integrity receipts. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the …

ParameterTypeDescription
start_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
end_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
site_urlstringrequired

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "bing_webmaster_dashboard",
    "arguments": {
      "site_url": "..."
    }
  }
}
calendar_connectorread-onlyexternal accessCalendar events across Google Calendar and Outlook: list upcoming meetings, search events, check …

Calendar events across Google Calendar and Outlook: list upcoming meetings, search events, check availability. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. …

ParameterTypeDescription
actionstringrequiredlist_my_calendar_events: List upcoming Google Calendar events | search_my_calendar: Search Google Calendar events by text | list_my_outlook_events: List upcoming Outlook calendar events. Requires Microsoft authentication | list_my_calendars: List all Google … One of: list_my_calendar_events, search_my_calendar, list_my_outlook_events, list_my_calendars, get_my_calendar_event, get_my_outlook_folders, list_my_outlook_calendars, get_my_outlook_event …
paramsobjectoptionalAction-specific parameters. list_my_calendar_events: {calendar_id?: string, max_results?: integer, time_min?: string, time_max?: string} | search_my_calendar: {query: string, calendar_id?: string, max_results?: integer} | list_my_outlook_events: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "calendar_connector",
    "arguments": {
      "action": "list_my_calendar_events"
    }
  }
}
calendly_connectorread-onlyexternal accessCalendly scheduling data: scheduled events, event types, invitee lists, and user availability. When the user …

Calendly scheduling data: scheduled events, event types, invitee lists, and user availability. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without a valid …

ParameterTypeDescription
actionstringrequiredlist_scheduled_events: List scheduled Calendly meetings/events with invitee and time details | list_event_types: List all Calendly event types (booking links) for the user | get_user: Get the authenticated Calendly user's profile and scheduling URL | … One of: list_scheduled_events, list_event_types, get_user, get_scheduled_event, list_event_invitees, list_organization_memberships, get_user_availability
paramsobjectoptionalAction-specific parameters. list_scheduled_events: {count?: integer, status?: string, min_start_time?: string, max_start_time?: string} | list_event_types: none | get_user: none | get_scheduled_event: {event_uuid: string} | list_event_invitees: {event_uuid: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "calendly_connector",
    "arguments": {
      "action": "list_scheduled_events"
    }
  }
}
callrail_connectorread-onlyexternal accessCallRail call-tracking read access via the CorpusIQ breadth tier (sourced through Nango, not a first-party …

CallRail call-tracking read access via the CorpusIQ breadth tier (sourced through Nango, not a first-party connector). Read-only: list accounts, companies, tracking numbers, and calls (with source, duration, and caller data). Call-attribution, phone-lead, and which-campaign-drove-calls questions. Writes are not exposed (default-deny). When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result …

ParameterTypeDescription
actionstringrequiredcallrail_list_accounts: List the CallRail accounts this connection can access. Returns each account's id and name. Call this first to resolve th | callrail_get_account: Get a single CallRail account summary by account_id (name, id, features). Requires … One of: callrail_list_accounts, callrail_get_account, callrail_list_companies, callrail_list_calls, callrail_list_trackers
paramsobjectoptionalAction-specific parameters. callrail_list_accounts: none | callrail_get_account: {account_id: string} | callrail_list_companies: {account_id: string} | callrail_list_calls: {account_id: string} | callrail_list_trackers: {account_id: string}

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "callrail_connector",
    "arguments": {
      "action": "callrail_list_accounts"
    }
  }
}
canonical_context_getread-onlyRead the user's declared CorpusIQ canonical facts, recent decisions, and declared metric specs. Use at the …

Read the user's declared CorpusIQ canonical facts, recent decisions, and declared metric specs. Use at the start of business, product, pricing, company, positioning, board, investor, factual, OR KPI/metric questions when stable user-approved truth may matter. This is read-only and returns only content the user deliberately saved. If declared metric specs are returned, prefer calling metric_spec_resolve(key=...) over computing the same KPI from raw connector tool calls. When tool output supplies …

ParameterTypeDescription
token_budgetintegeroptionalApproximate maximum context tokens to return. Default 1500.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "canonical_context_get",
    "arguments": {}
  }
}
canonical_decisions_addcan modifyPrepare a write to the canonical decisions log. IMPORTANT: this tool does not save immediately. Use when the …

Prepare a write to the canonical decisions log. IMPORTANT: this tool does not save immediately. Use when the user wants to log a decision or when you ask 'Log to canonical decisions?'. It returns a pending_write_id. Commit only after the user explicitly says yes by calling canonical_pending_commit. Never silently log decisions. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label …

ParameterTypeDescription
textstringrequiredDecision text to log.
contextstringoptionalOptional context explaining why this decision was made.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "canonical_decisions_add",
    "arguments": {
      "text": "..."
    }
  }
}
canonical_decisions_listread-onlyList recent canonical decisions for this user. Read-only. When tool output supplies an attribution footer, …

List recent canonical decisions for this user. Read-only. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal claims, or editorial …

ParameterTypeDescription
limitintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "canonical_decisions_list",
    "arguments": {}
  }
}
canonical_facts_getread-onlyGet one declared canonical business fact by key. Read-only. Use when the user asks for a stored fact such as …

Get one declared canonical business fact by key. Read-only. Use when the user asks for a stored fact such as pricing, connector count, tagline, team detail, certification, or product fact. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. …

ParameterTypeDescription
keystringrequiredCanonical fact key.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "canonical_facts_get",
    "arguments": {
      "key": "..."
    }
  }
}
canonical_facts_listread-onlyList declared canonical business facts, optionally filtered by category. Read-only. When tool output supplies …

List declared canonical business facts, optionally filtered by category. Read-only. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, …

ParameterTypeDescription
categorystringoptionalOptional fact category such as product, pricing, team, or taglines.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "canonical_facts_list",
    "arguments": {}
  }
}
canonical_facts_setcan modifyPrepare a write to a declared canonical fact. IMPORTANT: this tool does not save immediately. Call it only …

Prepare a write to a declared canonical fact. IMPORTANT: this tool does not save immediately. Call it only after proposing the exact fact to the user; it returns a pending_write_id. After the user explicitly answers yes in the same conversation, call canonical_pending_commit with that pending_write_id. Never silently save inferred or guessed facts. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep …

ParameterTypeDescription
keystringrequired
valuestringrequired
categorystringrequired

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "canonical_facts_set",
    "arguments": {
      "key": "...",
      "value": "...",
      "category": "general"
    }
  }
}
canonical_pending_cancelcan modifydestructiveCancel a pending canonical write when the user says no or changes their mind. When tool output supplies an …

Cancel a pending canonical write when the user says no or changes their mind. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal …

ParameterTypeDescription
pending_write_idstringrequired

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "canonical_pending_cancel",
    "arguments": {
      "pending_write_id": "..."
    }
  }
}
canonical_pending_commitcan modifydestructiveCommit a pending canonical fact or decision write after the user explicitly confirmed yes. Requires …

Commit a pending canonical fact or decision write after the user explicitly confirmed yes. Requires pending_write_id from canonical_facts_set or canonical_decisions_add. Do not call unless the user has just confirmed the exact pending write. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: …

ParameterTypeDescription
pending_write_idstringrequired
user_confirmationstringrequiredThe user's explicit confirmation text. Must be yes/confirmed/approve/approved.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "canonical_pending_commit",
    "arguments": {
      "pending_write_id": "...",
      "user_confirmation": "..."
    }
  }
}
chart_renderread-onlyRender numeric data as a deterministic CorpusIQ PNG plus a complete text summary. Use when the user asks to …

Render numeric data as a deterministic CorpusIQ PNG plus a complete text summary. Use when the user asks to visualize, chart, compare, or recap values already present in the conversation. Values remain explicitly unverified unless a live connector result supplied a chart_provenance token and every plotted value is mapped to its exact source_path (and secondary_source_path when applicable). A missing, expired, wrong-user, or mismatched receipt safely downgrades the chart to unverified …

ParameterTypeDescription
titlestringrequired
dataobject[]required
templatestringoptionalOne of: corpusiq-clean, metric-cards, comparison
chart_typestringoptionalauto draws a line when the labels are dates or periods and bars when they are ranked names; line and bar force the shape. One of: auto, line, bar
sourcestringoptionalDisplay label only; it is not treated as verified provenance.
provenance_tokenstringoptionalOpaque 15-minute token returned in a live connector result's chart_provenance object; bound to the authenticated user and tenant, valid across replicas.
widthintegeroptional
heightintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "chart_render",
    "arguments": {
      "title": "...",
      "data": []
    }
  }
}
close_connectorread-onlyexternal accessClose CRM sales platform: leads, opportunities (pipeline deals), activities (calls/emails/notes/meetings), …

Close CRM sales platform: leads, opportunities (pipeline deals), activities (calls/emails/notes/meetings), full-text search, and organization users (sales reps). Use for sales pipeline reporting, lead/contact lookup, rep-level activity attribution, and sales-funnel analytics. Auth: OAuth 2.0. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the …

ParameterTypeDescription
actionstringrequiredclose_list_leads: List leads in the connected Close CRM organization. Returns lead id, display_name, status_label, contacts, addresses, an | close_get_lead: Get a single Close CRM lead by id, including all custom fields, contacts, addresses, and opportunities … One of: close_list_leads, close_get_lead, close_list_opportunities, close_list_activities, close_search, close_list_users
paramsobjectoptionalAction-specific parameters. close_list_leads: {query?: string, limit?: integer, skip?: integer} | close_get_lead: {lead_id: string} | close_list_opportunities: {lead_id?: string, status_type?: string, limit?: integer, skip?: integer} | close_list_activities: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "close_connector",
    "arguments": {
      "action": "close_list_leads"
    }
  }
}
connect_gunbrokerread-onlyConnect your GunBroker seller account. Returns a browser URL to open the credential setup form. Use when the …

Connect your GunBroker seller account. Returns a browser URL to open the credential setup form. Use when the user says connect GunBroker, set up GunBroker, or link my GunBroker account. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do …

Takes no parameters.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "connect_gunbroker",
    "arguments": {}
  }
}
constantcontact_connectorread-onlyexternal accessConstant Contact email marketing: contacts, email campaigns, lists, and engagement metrics. When the user …

Constant Contact email marketing: contacts, email campaigns, lists, and engagement metrics. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without a valid …

ParameterTypeDescription
actionstringrequiredget_account_summary: Return the Constant Contact account summary: organisation name, contact email, phone, website, country, and optionally t | get_account_emails: Return email addresses registered on the Constant Contact account and their confirmation … One of: get_account_summary, get_account_emails, get_user_privileges, get_contacts, get_contact, search_contacts, get_lists, get_list …
paramsobjectoptionalAction-specific parameters. get_account_summary: {include_physical_address?: boolean, include_company_logo?: boolean} | get_account_emails: {confirm_status?: string} | get_user_privileges: none | get_contacts: {limit?: integer, status?: string, …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "constantcontact_connector",
    "arguments": {
      "action": "get_account_summary"
    }
  }
}
crm_connectorread-onlyexternal accessCustomer relationship management across HubSpot and LeadConnector: contacts, deals, pipelines, companies, and …

Customer relationship management across HubSpot and LeadConnector: contacts, deals, pipelines, companies, and sales opportunities. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves …

ParameterTypeDescription
actionstringrequiredlist_hubspot_contacts: List HubSpot contacts using legacy API pagination | search_hubspot_contacts: Search HubSpot contacts by keyword | list_hubspot_deals: List HubSpot deals with pagination | list_leadconnector_contacts: List LeadConnector contacts with … One of: list_hubspot_contacts, search_hubspot_contacts, list_hubspot_deals, list_leadconnector_contacts, get_hubspot_account_info, get_hubspot_contact, list_hubspot_companies, get_hubspot_company …
paramsobjectoptionalAction-specific parameters. list_hubspot_contacts: {limit?: integer, vid_offset?: integer} | search_hubspot_contacts: {query: string, limit?: integer} | list_hubspot_deals: {limit?: integer, offset?: integer} | list_leadconnector_contacts: {limit?: integer, …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "crm_connector",
    "arguments": {
      "action": "list_hubspot_contacts"
    }
  }
}
cross_source_ads_connectorread-onlyexternal accessCross-source analysis correlating Google Ads spend with GA4 web traffic and revenue. Use when comparing ad …

Cross-source analysis correlating Google Ads spend with GA4 web traffic and revenue. Use when comparing ad spend to sessions, conversions, or ROAS across platforms. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact …

ParameterTypeDescription
actionstringrequiredcorrelate_spend_vs_ga4_sessions: Cross-source: Google Ads daily spend/clicks/impressions vs GA4 web sessions and users by date. Shows whether paid ad act | correlate_conversions_vs_ga4_goals: Cross-source: Google Ads reported conversions vs GA4 conversion … One of: correlate_spend_vs_ga4_sessions, correlate_conversions_vs_ga4_goals, correlate_spend_vs_ga4_revenue
paramsobjectoptionalAction-specific parameters. correlate_spend_vs_ga4_sessions: {customer_id: string, property_id: string, start_date?: string, end_date?: string} | correlate_conversions_vs_ga4_goals: {customer_id: string, property_id: string, start_date?: string, end_date?: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "cross_source_ads_connector",
    "arguments": {
      "action": "correlate_spend_vs_ga4_sessions"
    }
  }
}
cross_source_email_connectorread-onlyexternal accessCross-source analysis correlating Klaviyo email activity with web traffic, ecommerce revenue, and ad spend. …

Cross-source analysis correlating Klaviyo email activity with web traffic, ecommerce revenue, and ad spend. Use for channel attribution, email-driven revenue, and unified marketing analytics. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map …

ParameterTypeDescription
actionstringrequiredcorrelate_email_vs_web_traffic: Cross-source: Klaviyo email sends vs GA4 web sessions by date. Shows whether email days drive traffic spikes | correlate_email_revenue_vs_ecommerce: Cross-source: Klaviyo email revenue vs Shopify/GA4 ecommerce revenue by date. … One of: correlate_email_vs_web_traffic, correlate_email_revenue_vs_ecommerce, correlate_email_vs_social_ads, get_channel_attribution_summary, correlate_list_growth_vs_youtube, correlate_form_signups_vs_ad_traffic, correlate_flow_revenue_vs_campaign_sends
paramsobjectoptionalAction-specific parameters. correlate_email_vs_web_traffic: {start_date?: string, end_date?: string} | correlate_email_revenue_vs_ecommerce: {start_date?: string, end_date?: string, external_shopify_data?: object} | correlate_email_vs_social_ads: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "cross_source_email_connector",
    "arguments": {
      "action": "correlate_email_vs_web_traffic"
    }
  }
}
dashboard_renderread-onlyexternal accessFetch live Google Analytics 4 data and return an evidence-backed CorpusIQ PNG recap plus accessible text, …

Fetch live Google Analytics 4 data and return an evidence-backed CorpusIQ PNG recap plus accessible text, structured values, reconciliation status, and an integrity receipt. The undimensioned current-period query remains the verified canonical KPI independently of daily/channel breakdown reconciliation. eventCount requires exact agreement; sessions distinguish matched, within-tolerance, bounded dimensional variance disclosed, and unverified breakdown states. Channel shares are calculated and …

ParameterTypeDescription
property_idstringrequiredGA4 property ID in properties/123456789 format.
start_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
end_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
metricstringoptionalOne of: sessions, eventCount
event_namestringoptionalOptional exact GA4 eventName filter; valid only with metric=eventCount.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "dashboard_render",
    "arguments": {
      "property_id": "..."
    }
  }
}
disable_connectorcan modifyHide a connector's tools from the active tool list for the current user. Use when the user says they don't …

Hide a connector's tools from the active tool list for the current user. Use when the user says they don't use a service or wants to pause a connector, such as 'disable Shopify' or 'hide TikTok'. The connector remains configured and can be restored with enable_connector. Disabled connectors still appear in get_connector_status marked Paused.

ParameterTypeDescription
connector_idstringrequiredConnector ID to disable. Examples: shopify, tiktok, ebay, microsoft, slack, google_ads, quickbooks, klaviyo.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "disable_connector",
    "arguments": {
      "connector_id": "..."
    }
  }
}
disconnect_gunbroker_connectioncan modifydestructiveRemove stored GunBroker credentials and disconnect the account. Use when the user says disconnect GunBroker, …

Remove stored GunBroker credentials and disconnect the account. Use when the user says disconnect GunBroker, remove GunBroker, or reset GunBroker. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign …

Takes no parameters.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "disconnect_gunbroker_connection",
    "arguments": {}
  }
}
drive_connectorread-onlyexternal accessFile storage across Google Drive, OneDrive, and Dropbox: list, search, and read user-uploaded documents, …

File storage across Google Drive, OneDrive, and Dropbox: list, search, and read user-uploaded documents, spreadsheets, PDFs, and other files. ONLY use this when the user explicitly asks about FILES, DOCUMENTS, or DRIVE contents (e.g. 'find my Q3 contract', 'list files in /Reports'). Do NOT use this to hunt for cached JSON or reports that might contain answers about other services (Shopify, GunBroker, QuickBooks, etc.) — call the corresponding service connector directly instead. When the user …

ParameterTypeDescription
actionstringrequiredsearch_drive: Search Google Drive files that the authenticated user has access to | list_drive_files: List files from Google Drive with pagination | search_my_onedrive: Search OneDrive files by name or content. Requires Microsoft authentication | … One of: search_drive, list_drive_files, search_my_onedrive, search_my_dropbox, read_sheet, get_drive_stats, get_file_content, get_my_onedrive_storage …
paramsobjectoptionalAction-specific parameters. search_drive: {query: string, max_results?: integer} | list_drive_files: {max_results?: integer, mime_type?: string, folder_id?: string} | search_my_onedrive: {query: string, max_results?: integer} | search_my_dropbox: {query: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "drive_connector",
    "arguments": {
      "action": "search_drive"
    }
  }
}
ebay_connectorread-onlyexternal accesseBay seller data: orders, transactions, seller standards, customer service metrics, traffic reports, and …

eBay seller data: orders, transactions, seller standards, customer service metrics, traffic reports, and funds summary. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified …

ParameterTypeDescription
actionstringrequiredget_orders: List eBay orders with GMV, item counts, and fulfillment status | get_seller_performance_overview: Get a consolidated eBay seller performance overview across standards, customer service metrics, and traffic | get_transactions: List eBay financial … One of: get_orders, get_seller_performance_overview, get_transactions, get_seller_standards_profile, get_customer_service_metric, get_traffic_report, get_seller_privileges, get_funds_summary
paramsobjectoptionalAction-specific parameters. get_orders: {limit?: integer, offset?: integer, filter_expr?: string} | get_seller_performance_overview: {program?: string, days?: integer} | get_transactions: {limit?: integer, filter_expr?: string} | get_seller_standards_profile: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "ebay_connector",
    "arguments": {
      "action": "get_orders"
    }
  }
}
email_connectorread-onlyexternal accessEmail messages across Gmail and Outlook: read, search, and list emails from any connected inbox. When the …

Email messages across Gmail and Outlook: read, search, and list emails from any connected inbox. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without a valid …

ParameterTypeDescription
actionstringrequiredlist_gmail_messages: List recent Gmail messages with optional query filter | search_gmail: Search Gmail messages using Gmail search syntax | list_my_outlook_emails: List recent Outlook/Microsoft 365 emails. Requires Microsoft authentication | … One of: list_gmail_messages, search_gmail, list_my_outlook_emails, search_my_outlook_emails, get_gmail_message, get_my_outlook_mailbox, read_my_outlook_email
paramsobjectoptionalAction-specific parameters. list_gmail_messages: {max_results?: integer, query?: string} | search_gmail: {query: string, max_results?: integer} | list_my_outlook_emails: {max_results?: integer, folder?: string, query?: string} | search_my_outlook_emails: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "email_connector",
    "arguments": {
      "action": "list_gmail_messages"
    }
  }
}
enable_connectorcan modifyRe-show a previously hidden connector's tools for the current user. Use when the user wants to restore a …

Re-show a previously hidden connector's tools for the current user. Use when the user wants to restore a paused connector, such as 'enable Shopify' or 'show TikTok again'. If the connector still needs authentication, get_connector_status will show the connect link.

ParameterTypeDescription
connector_idstringrequiredConnector ID to enable. Examples: shopify, tiktok, ebay, microsoft, slack, google_ads, quickbooks, klaviyo.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "enable_connector",
    "arguments": {
      "connector_id": "..."
    }
  }
}
featured_cash_recovery_engineread-onlyexternal accessBuild a structured 14-day cash-recovery plan: analyze overdue invoices in QuickBooks, cross-reference the …

Build a structured 14-day cash-recovery plan: analyze overdue invoices in QuickBooks, cross-reference the email threads with each customer, and pull contract terms from Drive, producing a prioritized collections sequence with drafted follow-ups. Use when the user asks how to collect overdue invoices, recover cash, chase receivables, 'who owes me money', or improve AR / collections. This is a CorpusIQ Skill: it returns a runbook (`skill_body`) to execute step-by-step, not the final answer — …

ParameterTypeDescription
user_questionstringoptionalOptional: the user's question in their own words, passed to the skill for context.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "featured_cash_recovery_engine",
    "arguments": {}
  }
}
featured_competitive_intelligence_briefread-onlyexternal accessCompile a structured competitive-intelligence brief: fetch competitors' websites, pricing pages, job …

Compile a structured competitive-intelligence brief: fetch competitors' websites, pricing pages, job postings, press releases, and product updates, then summarize positioning changes, hiring signals, and product moves. Use when the user asks to research / monitor / track a competitor, wants a 'competitive brief', 'what are competitors doing', or competitor positioning/pricing analysis. This is a CorpusIQ Skill: it returns a runbook (`skill_body`) to execute step-by-step, not the final answer — …

ParameterTypeDescription
user_questionstringoptionalOptional: the user's question in their own words, passed to the skill for context.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "featured_competitive_intelligence_brief",
    "arguments": {}
  }
}
featured_executive_summary_writerread-onlyexternal accessTurn analysis findings into a clear, actionable executive summary using the MAIN framework (Motive, Answer, …

Turn analysis findings into a clear, actionable executive summary using the MAIN framework (Motive, Answer, Impact, Next steps) and the Pyramid Principle. Use when the user has completed analysis and needs a stakeholder-ready write-up, asks for an 'executive summary', 'summarize this for leadership', a 'TL;DR for the board', or a decision-ready recap. Works from documents in Drive. This is a CorpusIQ Skill: it returns a runbook (`skill_body`) to execute step-by-step, not the final answer — …

ParameterTypeDescription
user_questionstringoptionalOptional: the user's question in their own words, passed to the skill for context.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "featured_executive_summary_writer",
    "arguments": {}
  }
}
featured_sales_call_prep_briefread-onlyexternal accessAssemble a one-page prep brief for an upcoming sales call: pull CRM deal history, past email threads, …

Assemble a one-page prep brief for an upcoming sales call: pull CRM deal history, past email threads, calendar history, and related documents, producing a compact brief with context, open items, and suggested talking points. Use when the user has a sales call / meeting coming up and wants to prepare, says 'prep me for my call with X', 'brief me on this account', or wants meeting prep from CRM + email. This is a CorpusIQ Skill: it returns a runbook (`skill_body`) to execute step-by-step, not the …

ParameterTypeDescription
user_questionstringoptionalOptional: the user's question in their own words, passed to the skill for context.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "featured_sales_call_prep_brief",
    "arguments": {}
  }
}
featured_seo_auditread-onlyexternal accessRun a full SEO audit of the user's site — technical health, on-page issues, meta tags, indexation, and …

Run a full SEO audit of the user's site — technical health, on-page issues, meta tags, indexation, and ranking diagnostics — and return a prioritized fix list. Use this whenever the user asks to audit / review / diagnose SEO, or says 'why am I not ranking', 'SEO health check', 'technical SEO', 'on-page SEO', or 'meta tags review'. Pulls live Search Console performance. This is a CorpusIQ Skill: it returns a runbook (`skill_body`) to execute step-by-step, not the final answer — follow its steps, …

ParameterTypeDescription
user_questionstringoptionalOptional: the user's question in their own words, passed to the skill for context.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "featured_seo_audit",
    "arguments": {}
  }
}
find_gunbroker_ffl_by_zipread-onlyexternal accessFind Federal Firearms Licensee (FFL) dealers near a buyer ZIP code. Useful for directing buyers to a local …

Find Federal Firearms Licensee (FFL) dealers near a buyer ZIP code. Useful for directing buyers to a local transfer dealer. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, …

ParameterTypeDescription
zip_codestringrequired5-digit US ZIP code
radius_milesintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "find_gunbroker_ffl_by_zip",
    "arguments": {
      "zip_code": "..."
    }
  }
}
ga4_connectorread-onlyexternal accessWeb and app analytics: traffic, sessions, users, conversions, real-time visitors, page performance, …

Web and app analytics: traffic, sessions, users, conversions, real-time visitors, page performance, acquisition sources, and revenue from GA4 properties. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so …

ParameterTypeDescription
actionstringrequiredget_report: Simple historical GA4 report: date-ranged sessions and active users, with an optional breakdown (channel/source/device) | list_properties: List GA4 properties (websites/apps). If account_id not provided, lists all properties from all accounts | … One of: get_report, list_properties, run_report, get_realtime, list_accounts
paramsobjectoptionalAction-specific parameters. get_report: {property_id: string, start_date?: string, end_date?: string, breakdown?: string} | list_properties: {account_id?: string} | run_report: {property_id: string, date_ranges: array, dimensions: array, metrics: array, …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "ga4_connector",
    "arguments": {
      "action": "get_report"
    }
  }
}
get_connector_statusread-onlyexternal accessReturn a pre-formatted Markdown dashboard showing every configured connector's status. IMPORTANT: The output …

Return a pre-formatted Markdown dashboard showing every configured connector's status. IMPORTANT: The output is a complete, ready-to-display Markdown table — show it to the user exactly as returned, do NOT summarize or paraphrase. Each row includes connector name, provider, connection status (with emoji indicators), and a clickable link to authenticate if needed. After displaying the table, offer to help the user connect any unauthorized services and mention they can say 'refresh status' after …

ParameterTypeDescription
connector_idstringoptionalOptional connector ID to filter results (e.g. 'google_workspace', 'quickbooks', 'hubspot', 'slack', 'ebay', 'dropbox', 'onedrive', 'outlook', 'shopify', 'facebook_marketing', 'tiktok', 'klaviyo', 'youtube', 'google_ads', 'postgres', 'mssql', 'cosmosdb', …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_connector_status",
    "arguments": {}
  }
}
get_gunbroker_account_summaryread-onlyexternal accessFetch the authenticated user GunBroker account profile, seller ratings, and account standing. When tool …

Fetch the authenticated user GunBroker account profile, seller ratings, and account standing. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, …

Takes no parameters.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_gunbroker_account_summary",
    "arguments": {}
  }
}
get_gunbroker_billing_summaryread-onlyexternal accessFetch recent GunBroker billing and fee records for the authenticated seller - listing fees, final value fees, …

Fetch recent GunBroker billing and fee records for the authenticated seller - listing fees, final value fees, and account charges. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, …

ParameterTypeDescription
daysintegeroptional
page_indexintegeroptional
page_sizeintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_gunbroker_billing_summary",
    "arguments": {}
  }
}
get_gunbroker_connection_statusread-onlyCheck whether GunBroker credentials are configured for the current user. Returns connection state, username, …

Check whether GunBroker credentials are configured for the current user. Returns connection state, username, and whether a valid AccessToken is cached. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing …

Takes no parameters.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_gunbroker_connection_status",
    "arguments": {}
  }
}
get_gunbroker_inventory_summaryread-onlyexternal accessReturn aggregate counts for the authenticated seller active GunBroker listings. Includes exact intersection …

Return aggregate counts for the authenticated seller active GunBroker listings. Includes exact intersection counts such as listings ending within the requested window that also have watchers. It scans paginated ItemsSelling results server-side and returns compact totals instead of raw listing pages. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into …

ParameterTypeDescription
page_sizeintegeroptional
max_pagesintegeroptional
ending_within_daysintegeroptionalOptional window for counting active listings ending within the next N days.
ending_within_hoursintegeroptionalOptional rolling-hour window for counting active listings ending soon.
ending_calendar_daysintegeroptionalOptional calendar-day window ending at 23:59:59 Eastern on the Nth day from now.
include_watched_listingsbooleanoptionalWhen true, include compact item-level rows for active listings with watchers.
watched_listing_limitintegeroptionalMaximum watched listing detail rows to return when include_watched_listings is true.
include_matching_listingsbooleanoptionalWhen true, include compact item-level rows matching requested ending/watchers/bids filters.
matching_listing_limitintegeroptional
watchers_onlybooleanoptionalWhen true, matching listings must have one or more watchers.
has_bidsbooleanoptionalOptional bid filter for matching listings.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_gunbroker_inventory_summary",
    "arguments": {}
  }
}
get_gunbroker_itemread-onlyexternal accessFetch full listing details for a single GunBroker item by ID - price, bids, watchers, seller, condition, and …

Fetch full listing details for a single GunBroker item by ID - price, bids, watchers, seller, condition, and description. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, …

ParameterTypeDescription
item_idintegerrequiredGunBroker item ID

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_gunbroker_item",
    "arguments": {
      "item_id": 0
    }
  }
}
get_gunbroker_orderread-onlyexternal accessFetch full details for a single GunBroker order - buyer, item, payment, shipping, and FFL transfer details. …

Fetch full details for a single GunBroker order - buyer, item, payment, shipping, and FFL transfer details. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, …

ParameterTypeDescription
order_idintegerrequiredGunBroker order ID

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_gunbroker_order",
    "arguments": {
      "order_id": 0
    }
  }
}
get_my_usage_statsread-onlyReturn personalized user statistics and a usage summary for the current user, showing the value they have …

Return personalized user statistics and a usage summary for the current user, showing the value they have received from CorpusIQ: total tool calls, skill invocations, single-source vs multi-source questions answered, plus their top connectors, top tools, and top skills. Use when the user asks for user stats, usage statistics, 'what have I used?', 'show me my activity', 'how much have I used CorpusIQ?', or wants a recap of their CorpusIQ activity.

ParameterTypeDescription
top_nintegeroptionalHow many of the user's top connectors / tools / skills to return.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_my_usage_stats",
    "arguments": {}
  }
}
get_my_youtube_analyticsread-onlyexternal accessGet analytics for the authenticated user's YouTube channel. When tool output supplies an attribution footer, …

Get analytics for the authenticated user's YouTube channel. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal claims, or editorial …

ParameterTypeDescription
start_datestringoptional
end_datestringoptional
dimensionsstring[]optional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_my_youtube_analytics",
    "arguments": {}
  }
}
get_my_youtube_channelread-onlyexternal accessGet the authenticated user's own YouTube channel details (title, subscriber count, video count, views). For …

Get the authenticated user's own YouTube channel details (title, subscriber count, video count, views). For Brand Account channels, ALWAYS pass channel_id explicitly — calling without channel_id only returns the OAuth identity's personal channel; YouTube does not resolve Brand Accounts via mine=true. Workflow for brands: get_youtube_channel(handle='@Brand') to resolve the id, then call this with channel_id set. Returns an explicit error envelope if the response is sparse/incomplete instead of …

ParameterTypeDescription
channel_idstringoptionalOptional channel ID to target a Brand Account (recommended for any non-personal channel)

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_my_youtube_channel",
    "arguments": {}
  }
}
get_my_youtube_geographyread-onlyexternal accessGet geographic viewer breakdown for the authenticated user's channel or a specific video. For Brand Accounts, …

Get geographic viewer breakdown for the authenticated user's channel or a specific video. For Brand Accounts, pass channel_id explicitly — channel==MINE does not resolve to Brand channels. Returns an explicit error envelope (not zero rows) when the Analytics API responds with no schema, which is the silent-fail signature. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; …

ParameterTypeDescription
start_datestringoptional
end_datestringoptional
video_idstringoptionalOptional video ID to filter to one video
channel_idstringoptionalOptional channel ID to target a Brand Account (required for any non-personal channel)

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_my_youtube_geography",
    "arguments": {}
  }
}
get_my_youtube_video_analyticsread-onlyexternal accessGet detailed analytics for a specific video owned by the authenticated user. For Brand Account videos, pass …

Get detailed analytics for a specific video owned by the authenticated user. For Brand Account videos, pass channel_id explicitly — channel==MINE does not resolve to Brand channels. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not …

ParameterTypeDescription
video_idstringrequired
start_datestringoptional
end_datestringoptional
channel_idstringoptionalOptional channel ID to target a Brand Account (required for any non-personal channel)

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_my_youtube_video_analytics",
    "arguments": {
      "video_id": "..."
    }
  }
}
get_my_youtube_videosread-onlyexternal accessList the authenticated user's own uploaded YouTube videos. When tool output supplies an attribution footer, …

List the authenticated user's own uploaded YouTube videos. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal claims, or editorial …

ParameterTypeDescription
max_resultsintegeroptional
page_tokenstringoptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_my_youtube_videos",
    "arguments": {}
  }
}
get_user_statisticsread-onlyAlias for get_my_usage_stats. Return personalized user statistics and a usage summary for the current user: …

Alias for get_my_usage_stats. Return personalized user statistics and a usage summary for the current user: total tool calls, skill invocations, question counts, top connectors, top tools, top skills, and token-savings estimates when available.

ParameterTypeDescription
top_nintegeroptionalHow many of the user's top connectors / tools / skills to return.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_user_statistics",
    "arguments": {}
  }
}
get_youtube_channelread-onlyexternal accessLook up a YouTube channel by ID, @handle, or legacy username. When tool output supplies an attribution …

Look up a YouTube channel by ID, @handle, or legacy username. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal claims, or editorial …

ParameterTypeDescription
channel_idstringoptional
handlestringoptional
usernamestringoptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_youtube_channel",
    "arguments": {}
  }
}
get_youtube_channel_videosread-onlyexternal accessGet recent videos from a YouTube channel. When tool output supplies an attribution footer, end your response …

Get recent videos from a YouTube channel. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal claims, or editorial labels such as …

ParameterTypeDescription
channel_idstringoptional
handlestringoptional
max_resultsintegeroptional
page_tokenstringoptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_youtube_channel_videos",
    "arguments": {}
  }
}
get_youtube_commentsread-onlyexternal accessGet top-level comments on a YouTube video. When tool output supplies an attribution footer, end your response …

Get top-level comments on a YouTube video. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal claims, or editorial labels such as …

ParameterTypeDescription
video_idstringrequired
max_resultsintegeroptional
orderstringoptional
page_tokenstringoptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_youtube_comments",
    "arguments": {
      "video_id": "..."
    }
  }
}
get_youtube_transcriptread-onlyexternal accessGet the transcript (captions) for a YouTube video. Returns timestamped segments and full text. When tool …

Get the transcript (captions) for a YouTube video. Returns timestamped segments and full text. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, …

ParameterTypeDescription
video_idstringrequired
languagestringoptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_youtube_transcript",
    "arguments": {
      "video_id": "..."
    }
  }
}
get_youtube_videoread-onlyexternal accessGet detailed information about one or more YouTube videos including title, description, view/like/comment …

Get detailed information about one or more YouTube videos including title, description, view/like/comment counts, duration, tags, and thumbnails. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign …

ParameterTypeDescription
video_idsstring[]requiredList of YouTube video IDs or URLs (max 50)

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "get_youtube_video",
    "arguments": {
      "video_ids": []
    }
  }
}
github_connectorread-onlyexternal accessRead-only GitHub delivery assessment, release forecasting, quality trends, scalar quality metrics, and a …

Read-only GitHub delivery assessment, release forecasting, quality trends, scalar quality metrics, and a native PNG dashboard with explicit evidence completeness. Auth: GitHub App user-to-server OAuth. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, …

ParameterTypeDescription
actionstringrequiredgithub_list_repositories: List repositories accessible through the connected GitHub App user grant. Read-only. Returns explicit evidence completen | github_assess_delivery_data: Assess milestone hygiene, scope, delivery velocity, reviews, and Actions from … One of: github_list_repositories, github_assess_delivery_data, github_get_release_forecast, github_get_quality_trend, github_get_release_quality_metric, github_release_quality_dashboard
paramsobjectoptionalAction-specific parameters. github_list_repositories: {max_pages?: integer} | github_assess_delivery_data: {owner: string, repository: string, since: string, until: string, max_pages?: integer, cadence_days?: integer} | github_get_release_forecast: {owner: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "github_connector",
    "arguments": {
      "action": "github_list_repositories"
    }
  }
}
github_release_quality_dashboardread-onlyexternal accessRender the native GitHub release-quality dashboard from the same validated forecast and quality facts used …

Render the native GitHub release-quality dashboard from the same validated forecast and quality facts used for text and structured output. Read-only. Returns explicit evidence completeness metadata. Partial or insufficient evidence yields no fabricated forecast, value, or score. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a …

ParameterTypeDescription
ownerstringrequired
repositorystringrequired
sincestringrequired
untilstringrequired
max_pagesintegeroptional
cadence_daysintegeroptional
milestone_numberintegerrequired
n_simsintegeroptional
seedintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "github_release_quality_dashboard",
    "arguments": {
      "owner": "...",
      "repository": "...",
      "since": "...",
      "until": "...",
      "milestone_number": 0
    }
  }
}
google_ads_connectorread-onlyexternal accessGoogle Ads performance: campaigns, ad groups, keywords, search terms, geographic and device breakdowns, …

Google Ads performance: campaigns, ad groups, keywords, search terms, geographic and device breakdowns, quality scores, impression share, and spend metrics. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so …

ParameterTypeDescription
actionstringrequiredget_account_summary: Get high-level Google Ads account performance summary with aggregate metrics | list_campaigns: List Google Ads campaigns with performance metrics (impressions, clicks, cost, conversions, CTR, CPC) | get_keyword_performance: Get keyword … One of: get_account_summary, list_campaigns, get_keyword_performance, list_accounts, get_campaign_performance, list_ad_groups, list_ads, get_search_terms …
paramsobjectoptionalAction-specific parameters. get_account_summary: {customer_id: string, start_date?: string, end_date?: string} | list_campaigns: {customer_id: string, start_date?: string, end_date?: string, status_filter?: string, limit?: integer} | get_keyword_performance: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "google_ads_connector",
    "arguments": {
      "action": "get_account_summary"
    }
  }
}
invoke_skillread-onlyexternal accessFetch a named CorpusIQ Skill runbook by id. IMPORTANT: this returns a PLAYBOOK (a step-by-step runbook), NOT …

Fetch a named CorpusIQ Skill runbook by id. IMPORTANT: this returns a PLAYBOOK (a step-by-step runbook), NOT the final answer. The response carries `status: runbook_returned`, `next_step: execute_runbook`, and `skill_body` with the ordered steps to execute. After receiving the runbook you MUST call the connector tools/actions it references to gather data, then synthesize a response for the user honoring any presentation rules in the runbook. Never present the raw runbook text to the user as the …

ParameterTypeDescription
skill_namestringrequiredThe id of the skill to invoke (from list_skills).
argumentsobjectoptionalJSON object of arguments matching the skill's input schema.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "invoke_skill",
    "arguments": {
      "skill_name": "..."
    }
  }
}
klaviyo_connectorread-onlyexternal accessEmail and SMS marketing automation: campaigns, flows, abandoned cart, list growth, subscriber health, …

Email and SMS marketing automation: campaigns, flows, abandoned cart, list growth, subscriber health, conversion metrics, and revenue attribution. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so …

ParameterTypeDescription
actionstringrequiredget_campaigns: List Klaviyo campaigns with performance metrics | get_email_metrics_summary: Get aggregated email campaign metrics: sends, opens, clicks, revenue | get_flows: List Klaviyo automation flows | get_abandoned_cart_flows: Get abandoned cart flow … One of: get_campaigns, get_email_metrics_summary, get_flows, get_abandoned_cart_flows, get_campaign_metrics, get_campaign_revenue, get_top_campaigns, get_flow_performance …
paramsobjectoptionalAction-specific parameters. get_campaigns: {start_date?: string, end_date?: string, channel?: string, limit?: integer} | get_email_metrics_summary: {start_date?: string, end_date?: string, interval?: string} | get_flows: {start_date?: string, end_date?: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "klaviyo_connector",
    "arguments": {
      "action": "get_campaigns"
    }
  }
}
linkedin_ads_connectorread-onlyexternal accessLinkedIn Marketing API (Ads): sponsored ad accounts, campaigns, creatives, and daily performance analytics …

LinkedIn Marketing API (Ads): sponsored ad accounts, campaigns, creatives, and daily performance analytics (impressions, clicks, costInLocalCurrency, conversions). Use for B2B paid-social reporting, LinkedIn campaign performance, and account-level ad spend. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it …

ParameterTypeDescription
actionstringrequiredget_account_info: Get the authenticated LinkedIn user's accessible ad-account memberships (account URN, role, user URN). Call this first t | list_ad_accounts: List all LinkedIn sponsored ad accounts the authenticated user can access. Returns id, name, … One of: get_account_info, list_ad_accounts, get_ad_account, list_campaigns, get_campaign, list_creatives, get_campaign_analytics, get_account_analytics
paramsobjectoptionalAction-specific parameters. get_account_info: none | list_ad_accounts: {limit?: integer} | get_ad_account: {account_id: string} | list_campaigns: {account_id: string, limit?: integer} | get_campaign: {campaign_id: string} | list_creatives: {campaign_id: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "linkedin_ads_connector",
    "arguments": {
      "action": "get_account_info"
    }
  }
}
list_gunbroker_categoriesread-onlyexternal accessList GunBroker item categories or subcategories. Use to discover valid category IDs for filtering search …

List GunBroker item categories or subcategories. Use to discover valid category IDs for filtering search results. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, …

ParameterTypeDescription
parent_idintegeroptionalParent category ID for subcategories

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_gunbroker_categories",
    "arguments": {}
  }
}
list_gunbroker_feedbackread-onlyexternal accessList feedback received by the authenticated GunBroker seller within the last N days - rating, comment, and …

List feedback received by the authenticated GunBroker seller within the last N days - rating, comment, and buyer. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, …

ParameterTypeDescription
daysintegeroptional
page_indexintegeroptional
page_sizeintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_gunbroker_feedback",
    "arguments": {}
  }
}
list_gunbroker_fraud_claimsread-onlyexternal accessList open fraud or dispute claims associated with the authenticated GunBroker seller account. When tool …

List open fraud or dispute claims associated with the authenticated GunBroker seller account. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, …

ParameterTypeDescription
page_indexintegeroptional
page_sizeintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_gunbroker_fraud_claims",
    "arguments": {}
  }
}
list_gunbroker_items_scheduledread-onlyexternal accessList GunBroker listings the authenticated seller has scheduled but not yet launched. When tool output …

List GunBroker listings the authenticated seller has scheduled but not yet launched. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, …

ParameterTypeDescription
page_indexintegeroptional
page_sizeintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_gunbroker_items_scheduled",
    "arguments": {}
  }
}
list_gunbroker_items_sellingread-onlyexternal accessList the authenticated seller currently active GunBroker listings - title, current price, bid count, …

List the authenticated seller currently active GunBroker listings - title, current price, bid count, watchers, and end date. Supports watcher/bid filters plus ending-window filtering across multiple pages. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the …

ParameterTypeDescription
page_indexintegeroptional
page_sizeintegeroptional
watchers_onlybooleanoptionalWhen true, only return listings with one or more watchers.
min_watchersintegeroptionalOptional minimum watcher threshold (e.g. 2 = only listings with 2+ watchers).
has_bidsbooleanoptionalOptional bid filter (true = with bids, false = no bids).
ending_within_daysintegeroptionalOptional rolling-day window. Return only listings ending within the next N days.
ending_within_hoursintegeroptionalOptional rolling-hour window. Return only listings ending within the next N hours.
ending_calendar_daysintegeroptionalOptional local calendar-day window ending at 23:59:59 Eastern on day N from now.
max_pagesintegeroptionalMaximum pages to scan starting at page_index when filters are set.
matching_listing_limitintegeroptionalMaximum filtered listing rows to return.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_gunbroker_items_selling",
    "arguments": {}
  }
}
list_gunbroker_items_soldread-onlyexternal accessList items the authenticated GunBroker seller sold within the last N days. Use to calculate revenue, AOV, and …

List items the authenticated GunBroker seller sold within the last N days. Use to calculate revenue, AOV, and sell-through by category. The GunBroker API only supports fixed windows (24h, 48h, 7, 14, 30, 60, 90 days); ``days`` is rounded up to the nearest supported window and capped at 90. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, …

ParameterTypeDescription
daysintegeroptional
page_indexintegeroptional
page_sizeintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_gunbroker_items_sold",
    "arguments": {}
  }
}
list_gunbroker_items_unsoldread-onlyexternal accessList the authenticated seller's expired (unsold) GunBroker listings within the last N days. Each item …

List the authenticated seller's expired (unsold) GunBroker listings within the last N days. Each item includes WatchersCount, so use this to answer 'did any recently ended listings have watchers?'. The GunBroker API only supports fixed windows (24h, 48h, 7, 14, 30, 60, 90 days); ``days`` is rounded up to the nearest supported window and capped at 90. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep …

ParameterTypeDescription
daysintegeroptional
page_indexintegeroptional
page_sizeintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_gunbroker_items_unsold",
    "arguments": {}
  }
}
list_gunbroker_ordersread-onlyexternal accessList GunBroker orders for the authenticated seller within the last N days - buyer info, item, amount, and …

List GunBroker orders for the authenticated seller within the last N days - buyer info, item, amount, and fulfillment status. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, …

ParameterTypeDescription
daysintegeroptional
page_indexintegeroptional
page_sizeintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_gunbroker_orders",
    "arguments": {}
  }
}
list_gunbroker_watched_itemsread-onlyexternal accessList GunBroker listings the authenticated user is watching. Useful for tracking competitor pricing or buying …

List GunBroker listings the authenticated user is watching. Useful for tracking competitor pricing or buying leads. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, …

ParameterTypeDescription
page_indexintegeroptional
page_sizeintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_gunbroker_watched_items",
    "arguments": {}
  }
}
list_my_youtube_channelsread-onlyexternal accessList YouTube channels the authenticated user owns or manages. Enumeration is incomplete by YouTube API design …

List YouTube channels the authenticated user owns or manages. Enumeration is incomplete by YouTube API design — non-CMS Brand Accounts are NOT returned. If an expected Brand Account is missing, use get_youtube_channel(handle='@Brand') to resolve its channel_id, then pass channel_id to other 'my_youtube_*' tools. Response includes brand_account_note explaining the gap. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query …

Takes no parameters.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_my_youtube_channels",
    "arguments": {}
  }
}
list_runbooksread-onlyexternal accessBrowse a compact list of CorpusIQ runbooks/skills. Do not use this to choose a runbook for a user's broad …

Browse a compact list of CorpusIQ runbooks/skills. Do not use this to choose a runbook for a user's broad question; call select_runbook first so the canonical semantic router can choose without sending the full catalog to the model. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat …

ParameterTypeDescription
querystringoptionalOptional text filter for browsing runbooks.
limitintegeroptionalMaximum runbooks to return. Default 10, max 25.
include_full_catalogbooleanoptionalSet true only when the user explicitly asks for the complete catalog.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_runbooks",
    "arguments": {}
  }
}
list_skillsread-onlyexternal accessBrowse a compact list of CorpusIQ Skills (cross-source runbooks). Do not use this to discover the best skill …

Browse a compact list of CorpusIQ Skills (cross-source runbooks). Do not use this to discover the best skill for a broad user question; call select_runbook first so Haiku can classify without sending the full skills catalog to the model. Use list_skills only when the user explicitly asks to browse available skills. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not …

ParameterTypeDescription
querystringoptionalOptional text filter for browsing skills.
limitintegeroptionalMaximum skills to return. Default 10, max 25.
include_full_catalogbooleanoptionalSet true only when the user explicitly asks for the complete catalog.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "list_skills",
    "arguments": {}
  }
}
logout_allcan modifydestructiveLog out of ALL connected data sources at once. Deletes all stored OAuth tokens for the current user and …

Log out of ALL connected data sources at once. Deletes all stored OAuth tokens for the current user and returns re-authentication links for each disconnected connector. Use this to fully reset your session or switch accounts across all services.

Takes no parameters.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "logout_all",
    "arguments": {}
  }
}
mailchimp_connectorread-onlyexternal accessMailchimp email marketing: campaigns, lists, subscribers, open rates, click rates, and audience growth. When …

Mailchimp email marketing: campaigns, lists, subscribers, open rates, click rates, and audience growth. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without …

ParameterTypeDescription
actionstringrequiredget_account: Get Mailchimp account root info including contact details, plan, and permissions | get_lists: List all audiences/lists in the Mailchimp account | get_list: Get details for a specific list/audience (name, stats, contact info, etc.) | … One of: get_account, get_lists, get_list, get_list_activity, get_list_growth_history, get_list_clients, get_list_merge_fields, get_list_interest_categories …
paramsobjectoptionalAction-specific parameters. get_account: {instance_id?: string} | get_lists: {offset?: integer, count?: integer, instance_id?: string} | get_list: {list_id: string, instance_id?: string} | get_list_activity: {list_id: string, instance_id?: string} | …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "mailchimp_connector",
    "arguments": {
      "action": "get_account"
    }
  }
}
mailchimp_dashboardread-onlyexternal accessFetch complete date-bounded Mailchimp campaign reports for one instance_id and return a verified PNG …

Fetch complete date-bounded Mailchimp campaign reports for one instance_id and return a verified PNG dashboard for sends, unique opens/clicks, unsubscribes, trend, and campaign breakdown. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do …

ParameterTypeDescription
start_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
end_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
instance_idstringoptionalOptional Mailchimp account label from list_mailchimp_accounts.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "mailchimp_dashboard",
    "arguments": {}
  }
}
meta_ads_connectorread-onlyexternal accessFacebook and Instagram advertising: campaigns, ad sets, ads, account-level spend, impressions, clicks, CPM, …

Facebook and Instagram advertising: campaigns, ad sets, ads, account-level spend, impressions, clicks, CPM, CPC, CTR, ROAS, and audience insights. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so …

ParameterTypeDescription
actionstringrequiredget_facebook_account: Get the authenticated Facebook user's profile (id, name, and email when Meta supplies it). Email may be null because the | get_facebook_account_insights: Get account-level Facebook Ads performance summary: impressions, clicks, spend, … One of: get_facebook_account, get_facebook_account_insights, list_facebook_campaigns, get_facebook_campaign_insights, list_facebook_ad_accounts, get_facebook_ad_account, get_facebook_campaign, list_facebook_ad_sets …
paramsobjectoptionalAction-specific parameters. get_facebook_account: none | get_facebook_account_insights: {start_date?: string, end_date?: string, date_preset?: string, account_id?: string} | list_facebook_campaigns: {limit?: integer, status_filter?: string, after?: string, …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "meta_ads_connector",
    "arguments": {
      "action": "get_facebook_account"
    }
  }
}
metric_spec_drift_reportread-onlyexternal accessWalk every metric spec for this user that has a non-empty cross_source_checks list, resolve each one and its …

Walk every metric spec for this user that has a non-empty cross_source_checks list, resolve each one and its comparison, and return ONLY the specs where the two values disagree beyond tolerance_percent. The 'what's silently disagreeing in my numbers' dashboard. Returns an empty list when everything is within tolerance — that's the green signal, not an error. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query …

Takes no parameters.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "metric_spec_drift_report",
    "arguments": {}
  }
}
metric_spec_getread-onlyFetch one metric spec by key — returns the full declaration including the expression DSL text, variables …

Fetch one metric spec by key — returns the full declaration including the expression DSL text, variables dict, cross_source_checks list, and metadata. Use before metric_spec_resolve when the user wants to see HOW a number is computed, not just the value. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data …

ParameterTypeDescription
keystringrequiredThe spec key (e.g. 'mrr', 'aov').

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "metric_spec_get",
    "arguments": {
      "key": "..."
    }
  }
}
metric_spec_listread-onlyList the user's declared metric specs (live computations such as MRR, AOV, monthly_active_customers). Each …

List the user's declared metric specs (live computations such as MRR, AOV, monthly_active_customers). Each entry includes the spec key, label, expected_unit, expression text, and version. Use this BEFORE computing any KPI from raw connector data — if a spec exists for the question, call metric_spec_resolve to get the canonical value instead of rolling your own aggregate. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and …

ParameterTypeDescription
unitstringoptionalOptional filter: only return specs with this expected_unit (e.g. 'USD', 'count').
owner_emailstringoptionalOptional filter by owner_email.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "metric_spec_list",
    "arguments": {}
  }
}
metric_spec_removecan modifyPrepare to delete a metric spec by key. IMPORTANT: this tool does not delete immediately. It returns a …

Prepare to delete a metric spec by key. IMPORTANT: this tool does not delete immediately. It returns a pending_write_id; the user must explicitly confirm via canonical_pending_commit before the spec is removed. Use only after summarizing which spec is being removed (key + label) and getting an explicit yes. Mirrors the canonical_facts pending-write pattern — never silently delete a canonical definition. When tool output supplies an attribution footer, end your response with that Markdown link …

ParameterTypeDescription
keystringrequiredThe spec key to remove (e.g. 'mrr', 'aov'). Case-sensitive, must match an existing spec.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "metric_spec_remove",
    "arguments": {
      "key": "..."
    }
  }
}
metric_spec_resolveread-onlyexternal accessCompute a metric spec NOW. Returns the live value, the spec version that produced it, the source-call ledger …

Compute a metric spec NOW. Returns the live value, the spec version that produced it, the source-call ledger (which connector tools were dispatched and how many rows each returned — NO row data is persisted), any drift detected against cross_source_checks, validation warnings, and the provenance footer string the renderer should append below the value. This is the hot path — call it whenever the user asks 'what is our <metric>?' and a spec exists for it. Result is NEVER cached; each call fires …

ParameterTypeDescription
keystringrequiredThe spec key to resolve (e.g. 'mrr').

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "metric_spec_resolve",
    "arguments": {
      "key": "..."
    }
  }
}
metric_spec_setcan modifyPrepare to save a new metric spec or a new version of an existing one. IMPORTANT: this tool does not save …

Prepare to save a new metric spec or a new version of an existing one. IMPORTANT: this tool does not save immediately. It returns a pending_write_id; the user must explicitly confirm via canonical_pending_commit before the write lands. Use only after proposing the exact spec (key + expression + expected_unit) and getting an explicit yes. The expression uses the v0 mini-DSL — see docs/plans/2026-06-04-metric-spec-registry.md §4 for the grammar. Soft validation (§13.Q2): a spec whose expression …

ParameterTypeDescription
keystringrequiredShort stable identifier (e.g. 'mrr').
labelstringrequiredHuman-readable label (e.g. 'Monthly Recurring Revenue').
descriptionstringoptionalThe user's own definition of what this metric means. Surfaced in the provenance footer.
expressionstringrequiredThe computation in the v0 mini-DSL. Example: stripe.list_subscriptions(status="active").aggregate(sum, field=plan.amount)
expected_unitstringrequiredFree-form unit string. Renderer uses for formatting: 'USD', 'count', 'ratio', 'percent', 'days'.
expected_freshnessstringoptionalOptional. Free text the user accepts as staleness budget: 'realtime', 'daily', 'monthly'. Metadata only — does NOT trigger caching.
cross_source_checksstring[]optionalOther metric spec keys whose result should match this one within tolerance_percent. Populates drift block on the resolve result. Empty = no cross-source check.
tolerance_percentnumberoptionalAbsolute percentage tolerance for cross_source_checks. Default 1.0. 0.0 for exact.
owner_emailstringoptionalWho is responsible for this definition (so reviewers know who to ping).
variablesobjectoptionalPer-spec substitution table for $user.<var> references inside the expression. Example: {"subscription_products": ["prod_growth"]}.
prefer_truth_sourcebooleanoptionalIf true and a TruthSource answers this key, the v0.1 resolver will use the truth source instead of executing the expression. v0 does NOT honor this flag yet — included so the spec is forward-compatible. Default false.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "metric_spec_set",
    "arguments": {
      "key": "...",
      "label": "...",
      "expression": "...",
      "expected_unit": "..."
    }
  }
}
monday_connectorread-onlyexternal accessMonday.com project and work management data: workspaces, boards, groups, columns, items, rows, pulses, …

Monday.com project and work management data: workspaces, boards, groups, columns, items, rows, pulses, owners, statuses, dates, blockers, and column values. Use for Monday.com board data and project/task status questions. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 …

ParameterTypeDescription
actionstringrequiredlist_workspaces: List Monday.com workspaces available to the connected user. Use this to discover workspace IDs before filtering boards | list_boards: List Monday.com boards available to the connected user, optionally filtered by workspace_id. Use this when … One of: list_workspaces, list_boards, get_board, list_items, get_item
paramsobjectoptionalAction-specific parameters. list_workspaces: none | list_boards: {limit?: integer, workspace_id?: integer} | get_board: {board_id: integer} | list_items: {board_id: integer, limit?: integer, projection?: object} | get_item: {item_id: integer}

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "monday_connector",
    "arguments": {
      "action": "list_workspaces"
    }
  }
}
notion_connectorread-onlyexternal accessNotion workspace: read pages, databases, blocks, and users. Search across the workspace, query databases, and …

Notion workspace: read pages, databases, blocks, and users. Search across the workspace, query databases, and traverse page block trees. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render …

ParameterTypeDescription
actionstringrequirednotion_get_user_info: Get the bot user associated with the connected Notion Internal Integration Token. Returns the bot user's id, name, type, | notion_list_users: List workspace users (members and guests) visible to the Notion integration. Returns id, name, … One of: notion_get_user_info, notion_list_users, notion_search, notion_list_databases, notion_query_database, notion_get_page, notion_get_block_children, notion_get_database
paramsobjectoptionalAction-specific parameters. notion_get_user_info: none | notion_list_users: {page_size?: integer, start_cursor?: string} | notion_search: {query?: string, filter_object?: string, page_size?: integer, start_cursor?: string} | notion_list_databases: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "notion_connector",
    "arguments": {
      "action": "notion_get_user_info"
    }
  }
}
odoo_connectorread-onlyexternal accessOdoo ERP/CRM data: partners (contacts and companies), sale orders, CRM leads and opportunities, …

Odoo ERP/CRM data: partners (contacts and companies), sale orders, CRM leads and opportunities, customer/vendor invoices, products, on-hand inventory, stock transfers, accounting journals, payments, taxes, employees, projects, and project tasks. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as …

ParameterTypeDescription
actionstringrequiredget_connection_info: Health check: returns the connected Odoo instance's server version, database name, and the authenticated user (id, name, | search_partners: Search Odoo partners (res.partner) — contacts and companies. Filter by free-text query against … One of: get_connection_info, search_partners, get_partner, list_sale_orders, get_sale_order, list_crm_leads, get_crm_lead, list_invoices …
paramsobjectoptionalAction-specific parameters. get_connection_info: none | search_partners: {query?: string, customers_only?: boolean, suppliers_only?: boolean, limit?: integer, offset?: integer} | get_partner: {partner_id: integer} | list_sale_orders: {state?: string, …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "odoo_connector",
    "arguments": {
      "action": "get_connection_info"
    }
  }
}
podium_connectorread-onlyexternal accessPodium read access via the CorpusIQ breadth tier (sourced through Nango, not a first-party connector). …

Podium read access via the CorpusIQ breadth tier (sourced through Nango, not a first-party connector). Read-only: locations, organizations, reviews, feedback, messaging conversations, and contacts. Reputation-management, online-review, and customer-messaging questions. Writes are not exposed (default-deny). When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified …

ParameterTypeDescription
actionstringrequiredlist_locations: List the Podium locations the connected user can access. Most other Podium data is scoped to a location. (Podium v4; sco | list_organizations: List the Podium organizations the connected user belongs to. (Podium v4; scope read_organizations.) … One of: list_locations, list_organizations, list_reviews, list_feedback, list_messages, list_contacts
paramsobjectoptionalAction-specific parameters. list_locations: none | list_organizations: none | list_reviews: none | list_feedback: none | list_messages: none | list_contacts: none

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "podium_connector",
    "arguments": {
      "action": "list_locations"
    }
  }
}
posthog_connectorread-onlyexternal accessPostHog product analytics: account/project info, raw events, person records, event definitions, HogQL …

PostHog product analytics: account/project info, raw events, person records, event definitions, HogQL queries, and funnel conversion analysis. Read-only via Personal API key (Path A). When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value …

ParameterTypeDescription
actionstringrequiredget_account_info: Get PostHog account and project metadata for the connected user. Returns the user email, organization name, project ID, | list_events: List recent raw events captured by PostHog for the project. Returns event ID, event name, distinct ID, … One of: get_account_info, list_events, list_persons, get_event_definitions, run_query, get_funnel
paramsobjectoptionalAction-specific parameters. get_account_info: none | list_events: {project_id?: integer, event?: string, after?: string, before?: string, limit?: integer} | list_persons: {project_id?: integer, search?: string, limit?: integer} | get_event_definitions: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "posthog_connector",
    "arguments": {
      "action": "get_account_info"
    }
  }
}
posthog_dashboardread-onlyexternal accessRun strict server-authored PostHog queries and return a verified PNG dashboard for events, exact unique …

Run strict server-authored PostHog queries and return a verified PNG dashboard for events, exact unique actors, daily trend, and top event types with complete reconciliation and receipts. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do …

ParameterTypeDescription
start_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
end_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
project_idintegeroptionalOptional PostHog project id; defaults to the connected project.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "posthog_dashboard",
    "arguments": {}
  }
}
postscript_connectorread-onlyexternal accessPostScript SMS marketing: subscribers, keywords, and shop analytics for Shopify merchants. When the user asks …

PostScript SMS marketing: subscribers, keywords, and shop analytics for Shopify merchants. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without a valid …

ParameterTypeDescription
actionstringrequiredget_subscribers: List PostScript SMS subscribers with optional filters for email, phone, Shopify customer ID, and date ranges | get_subscriber: Get a single PostScript SMS subscriber by ID | get_keywords: List all active SMS opt-in keywords for the PostScript … One of: get_subscribers, get_subscriber, get_keywords, get_keyword
paramsobjectoptionalAction-specific parameters. get_subscribers: {page?: integer, sort?: string, email?: string, phone_number?: string, shopify_customer_id?: string, created_at_gte?: string, created_at_lte?: string, updated_at_gte?: string, updated_at_lte?: string} | …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "postscript_connector",
    "arguments": {
      "action": "get_subscribers"
    }
  }
}
quickbooks_connectorread-onlyexternal accessFinancial accounting: profit & loss, invoices, balance sheet, accounts receivable/payable, payments, …

Financial accounting: profit & loss, invoices, balance sheet, accounts receivable/payable, payments, expenses, vendors, customers, and financial reports. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so …

ParameterTypeDescription
actionstringrequiredget_profit_loss: Get Profit and Loss (Income Statement) report | list_invoices: List invoices with optional date filters | get_overdue_invoices: Get overdue invoices with open balance, sorted by days overdue | get_balance_sheet: Get Balance Sheet report: … One of: get_profit_loss, list_invoices, get_overdue_invoices, get_balance_sheet, get_company_info, list_customers, get_customer, search_customers …
paramsobjectoptionalAction-specific parameters. get_profit_loss: {start_date?: string, end_date?: string} | list_invoices: {max_results?: integer, start_position?: integer, start_date?: string, end_date?: string} | get_overdue_invoices: {max_results?: integer} | …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "quickbooks_connector",
    "arguments": {
      "action": "get_profit_loss"
    }
  }
}
quickbooks_dashboardread-onlyexternal accessFetch request-local QuickBooks Profit and Loss, Balance Sheet, historical AR/AP aging, and company reports, …

Fetch request-local QuickBooks Profit and Loss, Balance Sheet, historical AR/AP aging, and company reports, then return a verified PNG dashboard with reconciled facts, accessible text, and integrity receipts. Inputs: optional start_date and end_date. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy …

ParameterTypeDescription
start_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
end_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "quickbooks_dashboard",
    "arguments": {}
  }
}
remove_my_youtube_brand_channelcan modifydestructiveDrop a registered YouTube Brand Account channel from the user's registrations. If the removed brand was the …

Drop a registered YouTube Brand Account channel from the user's registrations. If the removed brand was the primary, primary status falls back to the oldest remaining registered brand. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do …

ParameterTypeDescription
channel_idstringrequiredChannel ID (UC...) of the registered brand to remove

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "remove_my_youtube_brand_channel",
    "arguments": {
      "channel_id": "..."
    }
  }
}
reset_connector_tokencan modifydestructiveReset connector auth state for the current user. Use when tokens are stale, missing scopes, tied to the wrong …

Reset connector auth state for the current user. Use when tokens are stale, missing scopes, tied to the wrong account/workspace, or repeatedly failing auth. For credential-based connectors, this clears the saved credentials so the user can re-enter them. Input: connector_id (required). Supported values: google_workspace, microsoft, dropbox, shopify, shopline, quickbooks, hubspot, slack, ebay, facebook_marketing, tiktok, klaviyo, calendly, activecampaign, odoo, constantcontact, airtable, …

ParameterTypeDescription
connector_idstringrequiredConnector token to reset (e.g., 'slack', 'tiktok', 'klaviyo', 'google_workspace', 'microsoft', 'gohighlevel').

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "reset_connector_token",
    "arguments": {
      "connector_id": "..."
    }
  }
}
resolve_connectorread-onlyexternal accessDiscover how to answer the user's data question. ALWAYS call this FIRST for any data-related request. For …

Discover how to answer the user's data question. ALWAYS call this FIRST for any data-related request. For broad questions — business health, performance, growth, financial pulse, recap, 'how are we doing', 'what should I focus on', or any cross-source question — the response returns a CorpusIQ Skill in `skill.skill_body`: a pre-built runbook you should execute step-by-step, honoring any presentation rules it specifies. For narrow single-source questions, the response returns 2-4 ready-to-call …

ParameterTypeDescription
intentstringrequiredNatural language description of what you want to do. Examples: 'check GA4 traffic this week', 'show me overdue invoices', 'compare ad spend to revenue'.
connector_hintstringoptionalOptional explicit connector name if the user specifies one. Examples: 'quickbooks', 'shopify', 'ga4', 'slack'.
multibooleanoptionalSet true to allow returning tools from multiple connector groups for cross-source queries.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "resolve_connector",
    "arguments": {
      "intent": "..."
    }
  }
}
run_runbookread-onlyexternal accessRun a specific CorpusIQ runbook by id. By default this returns the playbook (`skill_body`) for client-side …

Run a specific CorpusIQ runbook by id. By default this returns the playbook (`skill_body`) for client-side execution. Set execution_mode=server_side for the bounded executive-snapshot pilot; unsupported runbooks fail closed. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields …

ParameterTypeDescription
runbook_idstringrequiredThe runbook id to execute (from list_runbooks/select_runbook).
versionstringoptionalExact governed runbook version. Required for server_side execution; ignored in playbook mode.
content_hashstringoptionalExact governed runbook SHA-256 content hash. Required for server_side execution; ignored in playbook mode.
user_questionstringoptionalOriginal user question for execution context.
date_rangestringoptionalOptional date window hint like 'last_30_days'.
modestringoptionalOptional output depth mode. One of: summary, detailed, diagnostic
argumentsobjectoptionalOptional explicit runbook argument object.
execution_modestringoptionalplaybook preserves the existing client-executed response. server_side runs the bounded executive-snapshot pilot. One of: playbook, server_side

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "run_runbook",
    "arguments": {
      "runbook_id": "..."
    }
  }
}
salesforce_connectorread-onlyexternal accessSalesforce CRM read access via the CorpusIQ breadth tier (sourced through Arcade, not a first-party …

Salesforce CRM read access via the CorpusIQ breadth tier (sourced through Arcade, not a first-party connector). Read-only: search opportunities, leads, contacts; pull pre-joined account 360s; inspect a single opportunity; list tasks; resolve the current user. Pipeline, forecast, deals-at-risk, account-history questions. Writes are intentionally not exposed (default-deny). When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this …

ParameterTypeDescription
actionstringrequiredsalesforce_get_account_by_id: Gets the account with related info: contacts, leads, notes, calls, opportunities, tasks, emails, and events (up to 10 it | salesforce_get_account_by_keywords: Searches for accounts in Salesforce and returns them with related … One of: salesforce_get_account_by_id, salesforce_get_account_by_keywords, salesforce_get_opportunity_by_id, salesforce_list_my_tasks, salesforce_search_contacts, salesforce_search_leads, salesforce_search_opportunities, salesforce_whoami
paramsobjectoptionalAction-specific parameters. salesforce_get_account_by_id: {account_id: string} | salesforce_get_account_by_keywords: {query: string, limit?: integer, page?: integer} | salesforce_get_opportunity_by_id: {opportunity_id: string} | salesforce_list_my_tasks: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "salesforce_connector",
    "arguments": {
      "action": "salesforce_get_account_by_id"
    }
  }
}
search_console_connectorread-onlyexternal accessSEO and search performance: clicks, impressions, CTR, position, sitemaps, URL inspection, and indexed page …

SEO and search performance: clicks, impressions, CTR, position, sitemaps, URL inspection, and indexed page status from Google Search Console. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render …

ParameterTypeDescription
actionstringrequiredget_sites: List all properties (sites) verified in Google Search Console | get_performance: Query search performance data from Google Search Console: clicks, impressions, CTR, and average position. Group by query | get_sitemaps: List sitemaps submitted to … One of: get_sites, get_performance, get_sitemaps, inspect_url
paramsobjectoptionalAction-specific parameters. get_sites: none | get_performance: {site_url: string, start_date: string, end_date: string, dimensions?: array, row_limit?: integer, start_row?: integer, dimension_filter_groups?: array, search_type?: string} | get_sitemaps: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "search_console_connector",
    "arguments": {
      "action": "get_sites"
    }
  }
}
search_gunbroker_itemsread-onlyexternal accessSearch GunBroker marketplace listings by keyword, category, price range, or condition. Use to find comps, …

Search GunBroker marketplace listings by keyword, category, price range, or condition. Use to find comps, research pricing, or survey inventory. No credentials required. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or …

ParameterTypeDescription
keywordsstringoptionalFree-text search query
category_idintegeroptionalGunBroker category ID
conditionintegeroptional1=New, 2=Used
min_pricenumberoptional
max_pricenumberoptional
page_indexintegeroptional
page_sizeintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "search_gunbroker_items",
    "arguments": {}
  }
}
search_youtuberead-onlyexternal accessSearch YouTube for videos by query. When tool output supplies an attribution footer, end your response with …

Search YouTube for videos by query. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal claims, or editorial labels such as 'waste'. …

ParameterTypeDescription
querystringrequired
max_resultsintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "search_youtube",
    "arguments": {
      "query": "..."
    }
  }
}
select_runbookread-onlyexternal accessUse this FIRST for broad executive/business questions such as 'How healthy is my business?', 'How are we …

Use this FIRST for broad executive/business questions such as 'How healthy is my business?', 'How are we doing?', 'What should I focus on?', or 'Give me an executive summary'. Selects the best CorpusIQ runbook and returns the next step. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat …

ParameterTypeDescription
user_questionstringrequiredThe user's plain-language business question.
connected_sourcesstring[]optionalOptional hint list of currently connected data sources.
preferred_scopestringoptionalOptional analysis scope hint. One of: business, marketing, finance, operations, customer, unknown

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "select_runbook",
    "arguments": {
      "user_question": "..."
    }
  }
}
semrush_connectorread-onlyexternal accessSemrush SEO platform: domain overview, organic and paid keywords, competitor analysis, backlinks, and keyword …

Semrush SEO platform: domain overview, organic and paid keywords, competitor analysis, backlinks, and keyword research. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified …

ParameterTypeDescription
actionstringrequiredget_domain_overview: Get domain-level organic and paid traffic summary from Semrush. Returns the domain's estimated organic keyword count, or | get_organic_keywords: Get top organic (SEO) keywords that a domain ranks for in Semrush. Returns keyword, ranking … One of: get_domain_overview, get_organic_keywords, get_paid_keywords, get_competitors, get_backlinks_overview, get_keyword_overview, get_domain_history
paramsobjectoptionalAction-specific parameters. get_domain_overview: {domain: string, database?: string} | get_organic_keywords: {domain: string, database?: string, limit?: integer, offset?: integer} | get_paid_keywords: {domain: string, database?: string, limit?: integer, …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "semrush_connector",
    "arguments": {
      "action": "get_domain_overview"
    }
  }
}
semrush_dashboardread-onlyexternal accessFetch live Semrush domain, history, backlink, and competitor reports and return a source-verified, …

Fetch live Semrush domain, history, backlink, and competitor reports and return a source-verified, non-authoritative estimate dashboard with explicit top-N coverage and integrity receipts. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. …

ParameterTypeDescription
domainstringrequired
databasestringoptional
monthsintegeroptional

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "semrush_dashboard",
    "arguments": {
      "domain": "..."
    }
  }
}
set_my_primary_youtube_channelcan modifydestructiveChange which already-registered Brand Account is the user's primary. The primary brand is the default target …

Change which already-registered Brand Account is the user's primary. The primary brand is the default target for per-channel my_youtube_* tools when no channel_id is supplied. At most one primary per user; setting a new primary unsets the previous one. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy …

ParameterTypeDescription
channel_idstringrequiredChannel ID (UC...) of an already-registered brand to mark as primary

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "set_my_primary_youtube_channel",
    "arguments": {
      "channel_id": "..."
    }
  }
}
shopify_dashboardread-onlyexternal accessFetch complete date-bounded Shopify orders and shop metadata, then return a verified PNG dashboard for booked …

Fetch complete date-bounded Shopify orders and shop metadata, then return a verified PNG dashboard for booked order value, order count, AOV, trend, and status breakdown with reconciliation and receipts. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool …

ParameterTypeDescription
start_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
end_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "shopify_dashboard",
    "arguments": {}
  }
}
shopline_connectorread-onlyexternal accessSHOPLINE ecommerce data: store profile, orders, refunds, products, inventory, locations, customers, returns, …

SHOPLINE ecommerce data: store profile, orders, refunds, products, inventory, locations, customers, returns, fulfillment orders, and discount-code price rules. Read-only first-party connector using merchant-scoped OAuth. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, …

ParameterTypeDescription
actionstringrequiredget_store_info: Get connected SHOPLINE store identity, currency, timezone, status, domain, language, and contact fields. Read-only | list_orders: List SHOPLINE orders with totals, payment and fulfillment state, customer, line items, refunds, and pagination … One of: get_store_info, list_orders, get_order, get_order_summary, get_order_refunds, list_products, get_product, get_inventory_items …
paramsobjectoptionalAction-specific parameters. get_store_info: none | list_orders: {limit?: integer, page_info?: string, financial_status?: string, fulfillment_status?: string, status?: string, created_at_min?: string, created_at_max?: string} | get_order: {order_id: string} | …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "shopline_connector",
    "arguments": {
      "action": "get_store_info"
    }
  }
}
slack_connectorread-onlyexternal accessSlack workspace data: channels, messages, threads, files, and workspace analytics. When the user asks for a …

Slack workspace data: channels, messages, threads, files, and workspace analytics. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without a valid connector …

ParameterTypeDescription
actionstringrequiredlist_channels: List Slack channels accessible to the authenticated user | search_messages: Search Slack messages by query | get_workspace_analytics: Get aggregate Slack workspace analytics (channels, members, top channels) | get_workspace_info: Get metadata … One of: list_channels, search_messages, get_workspace_analytics, get_workspace_info, get_thread, search_files
paramsobjectoptionalAction-specific parameters. list_channels: {limit?: integer, exclude_archived?: boolean} | search_messages: {query: string, count?: integer} | get_workspace_analytics: {channel_limit?: integer} | get_workspace_info: none | get_thread: {channel_id: string, …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "slack_connector",
    "arguments": {
      "action": "list_channels"
    }
  }
}
stripe_connectorread-onlyexternal accessStripe payments platform: account profile, charges, customers, payouts, balance transactions, refunds, …

Stripe payments platform: account profile, charges, customers, payouts, balance transactions, refunds, disputes, and balance. Read-only via restricted API key (Path A). Phase 2A adds the reconciliation block: payouts, balance transactions, refunds, disputes, and balance — the primitives needed for QuickBooks-style payout reconciliation and Shopify-style settlement gap analysis. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by …

ParameterTypeDescription
actionstringrequiredget_account: Get the authenticated Stripe account profile: business name, country, default currency, charges/payouts enabled status, | list_charges: List Stripe charges (payments) with cursor pagination. Returns charge id, amount (in smallest currency unit, … One of: get_account, list_charges, list_customers, list_payouts, get_payout, list_balance_transactions, list_refunds, get_refund …
paramsobjectoptionalAction-specific parameters. get_account: none | list_charges: {limit?: integer, starting_after?: string, created_after?: integer} | list_customers: {limit?: integer, starting_after?: string, email?: string} | list_payouts: {limit?: integer, starting_after?: …

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "stripe_connector",
    "arguments": {
      "action": "get_account"
    }
  }
}
stripe_dashboardread-onlyexternal accessFetch complete date-bounded Stripe balance transactions and account metadata, then return a verified PNG …

Fetch complete date-bounded Stripe balance transactions and account metadata, then return a verified PNG dashboard with integer minor-unit facts, currency exponent, reconciliation, accessible text, and an integrity receipt. Inputs: optional start_date and end_date. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. …

ParameterTypeDescription
start_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.
end_datestringoptionalYYYY-MM-DD, today, yesterday, or NdaysAgo.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "stripe_dashboard",
    "arguments": {}
  }
}
tiktok_connectorread-onlyexternal accessTikTok account and video analytics: profile stats, video performance, engagement metrics (views, likes, …

TikTok account and video analytics: profile stats, video performance, engagement metrics (views, likes, shares, comments). When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified …

ParameterTypeDescription
actionstringrequiredget_account_analytics: Get TikTok account-level analytics: total videos posted, total likes received, follower count, and following count | list_videos: List the authenticated user's posted TikTok videos with engagement metrics (views, likes, comments, … One of: get_account_analytics, list_videos, get_video_analytics, get_profile, get_video_details
paramsobjectoptionalAction-specific parameters. get_account_analytics: none | list_videos: {max_count?: integer, cursor?: integer} | get_video_analytics: none | get_profile: none | get_video_details: {video_ids: array}

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "tiktok_connector",
    "arguments": {
      "action": "get_account_analytics"
    }
  }
}
truth_sources_listread-onlyList the user's registered Source-of-Truth Manifest entries. These are pointers to user-maintained …

List the user's registered Source-of-Truth Manifest entries. These are pointers to user-maintained authoritative documents (KPI workbooks, pricing sheets, contracts, customer masters) that the user has declared to be authoritative for specific questions. CRITICAL: Call this tool FIRST, before any analysis of unit economics, vendor cost, marketing efficiency, attribution, or financial performance. If a relevant manifest entry exists, use the referenced tool in 'retrieval_tool' to fetch the …

Takes no parameters.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "truth_sources_list",
    "arguments": {}
  }
}
truth_sources_registercan modifyPrepare to register a new Source-of-Truth Manifest entry that points at a user-maintained authoritative …

Prepare to register a new Source-of-Truth Manifest entry that points at a user-maintained authoritative document. IMPORTANT: This tool does not save immediately. It returns a pending_write_id that the user must explicitly confirm before the entry is committed (same pattern as canonical_facts_set). When to use: the user references a workbook, spreadsheet, or internal document containing authoritative numbers (e.g. 'I keep my unit economics in a Google Sheet', 'pricing is in this PDF'). Stage the …

ParameterTypeDescription
keystringrequiredShort stable identifier for this source. Examples: 'unit_economics_workbook', 'pricing_sheet', 'agency_contract'. Re-registering the same key overwrites the previous entry.
labelstringrequiredHuman-readable label the user gave the document.
locationstringrequiredResource pointer: 'drive://<file_id>', 'onedrive://<item_id>', 'dropbox://<path>', 'sharepoint://<site>/<file>', or 'url://<https>'. Never embed inline document content.
answersstring[]requiredList of canonical questions this source authoritatively answers. Used by the AI to decide which manifest entry to consult.
retrieval_toolstringrequiredMCP tool name the AI should call to fetch the document. e.g. 'get_file_content' for Drive, 'get_my_onedrive_file_content' for OneDrive.
refresh_cadencestringoptionalOptional. e.g. 'weekly', 'monthly', 'updated manually'.
notesstringoptionalOptional caveats or usage notes.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "truth_sources_register",
    "arguments": {
      "key": "...",
      "label": "...",
      "location": "...",
      "answers": [],
      "retrieval_tool": "..."
    }
  }
}
truth_sources_removecan modifyPrepare to remove a Source-of-Truth Manifest entry. IMPORTANT: This tool does not delete immediately. It …

Prepare to remove a Source-of-Truth Manifest entry. IMPORTANT: This tool does not delete immediately. It returns a pending_write_id that the user must explicitly confirm. On user confirmation, call canonical_pending_commit. Use when the user says the document moved, was deleted, or is no longer authoritative. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn …

ParameterTypeDescription
keystringrequiredThe truth-source key to remove.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "truth_sources_remove",
    "arguments": {
      "key": "..."
    }
  }
}
web_fetch_connectorread-onlyexternal accessGrounded public-web retrieval: fetch any public web page and return its cleaned text, title, and description, …

Grounded public-web retrieval: fetch any public web page and return its cleaned text, title, and description, each cited to the source URL and timestamped. CorpusIQ retrieves the real page content BEFORE the model reasons over it, so answers about a competitor's website, pricing page, about/careers page, or any public URL are based on fetched text — never guessed. A field the page did not contain is returned as 'unavailable'; the tool never fabricates a value. When the user asks for a visual, …

ParameterTypeDescription
actionstringrequiredfetch_url: Fetch a public web page and return its cleaned text plus title and description, each cited to the source URL and timesta | fetch_social_profile: Fetch grounded PUBLIC stats for a social media profile — follower count, post count, following count, … One of: fetch_url, fetch_social_profile
paramsobjectoptionalAction-specific parameters. fetch_url: {url: string} | fetch_social_profile: {url: string}

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "web_fetch_connector",
    "arguments": {
      "action": "fetch_url"
    }
  }
}

Resources 60

Badge

Maintain this server? Put its live status in your README:

MCP status badge

[![MCP status](https://mcp.aianytime.net/badge/corpusiq.svg)](https://mcp.aianytime.net/s/corpusiq/)

Edit this entry · Report a problem

More in Cloud, ops & data

Checks record what a server answered, not whether it is safe. A listing is not a security audit; read a server's source and permissions before you connect it. Add a server · JSON · llms.txt · llms-full.txt

Browse: Agents, IDEs & developer tools · Search & discovery · Knowledge, memory & context · Media & generation · Security · Finance & markets · Marketing, content & social · Cloud, ops & data · Commerce, travel & logistics · Work & productivity · No account needed · Local servers