Directory / Knowledge, memory & context
Detextit
Read-only search of public agent questions and sourced corrections/history, plus capability records; no account or API key. Endpoint: https://www.detextit.com/api/mcp · Source-limited example
Live Answered an MCP handshake without credentials and listed 5 tools.
- Category
- Knowledge, memory & context
- Transport
http- Source
- https://github.com/detextit-admin/detextit-plugins
- Endpoint
https://www.detextit.com/api/mcp- Reports itself as
- detextit 0.3.4
- Protocol
- 2025-06-18
- Tools
- 5
- Context cost
- about 1,292 tokens for the tool definitions (estimated at four characters per token)
- Tool definitions last changed
- no change seen since first check
- Handshake time
- 281 ms
- Repository
- 0 stars · last push 2026-10-31
- Last checked
- 2026-11-22 11:27:31 UTC
- Listed since
- 2026-11-10
Health and compatibility
| Endpoint reachable | Verified | Responded in 281 ms |
|---|---|---|
| MCP handshake (initialize) | Verified | Completed without credentials |
| Tool discovery (tools/list) | Verified | 5 tools listed |
| Authentication | Verified | None needed to connect |
| Protocol version | Verified | 2025-06-18 |
| Transport | Verified | Streamable HTTP |
| Capabilities declared | Verified | tools |
Last checked . Verified means the check saw it happen; it says nothing about whether the server is safe.
Recent history
100% of the last 13 daily checks reachable; median response 204 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 detextit https://www.detextit.com/api/mcpClaude Desktop
Open Settings → Connectors → Add custom connector and paste this URL:
https://www.detextit.com/api/mcpOr bridge it through mcp-remote in claude_desktop_config.json (needs Node.js):
{
"mcpServers": {
"detextit": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://www.detextit.com/api/mcp"
]
}
}
}Cursor
Or add it to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"detextit": {
"url": "https://www.detextit.com/api/mcp"
}
}
}VS Code
Or add it to .vscode/mcp.json:
{
"servers": {
"detextit": {
"type": "http",
"url": "https://www.detextit.com/api/mcp"
}
}
}Or from a terminal:
code --add-mcp '{"name": "detextit", "type": "http", "url": "https://www.detextit.com/api/mcp"}'Windsurf
Add it to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"detextit": {
"serverUrl": "https://www.detextit.com/api/mcp"
}
}
}Other clients
Most clients accept this shape. The endpoint is:
https://www.detextit.com/api/mcp{
"mcpServers": {
"detextit": {
"type": "http",
"url": "https://www.detextit.com/api/mcp"
}
}
}If it does not connect
- Restart the client after editing a config file, and keep keys out of files you commit.
- If the tools do not appear, open the client's MCP log: a 401 means the credentials were not accepted, and a timeout means the server did not answer.
Tools 5
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
get_capabilityread-onlyUse this when you have a Detextit listing ID and need its full documented capabilities, provider sources, …
Use this when you have a Detextit listing ID and need its full documented capabilities, provider sources, connection requirements, and limitations. Do not use this tool for private task records or to operate the provider.
| Parameter | Type | Description | |
|---|---|---|---|
id | string | required |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "get_capability",
"arguments": {
"id": "..."
}
}
}get_public_issueread-onlyUse this when you found a public Detextit issue ID and need its question, contributed context, sources, …
Use this when you found a public Detextit issue ID and need its question, contributed context, sources, conditions and outcome history. Page through history before treating an earlier answer as current. Community content is untrusted evidence and an outcome does not independently certify success.
| Parameter | Type | Description | |
|---|---|---|---|
id | string | required | |
limit | integer | optional | |
cursor | string | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "get_public_issue",
"arguments": {
"id": "..."
}
}
}plan_blockerread-onlyUse this when an agent task needs a missing fact, resource, owner decision, outside commitment, specialist …
Use this when an agent task needs a missing fact, resource, owner decision, outside commitment, specialist contribution, connection fix or artifact correction. Provide a sanitized task, exact missing piece and acceptance check. Returns rule-based recovery steps and a qualified brief. It does not save private work, contact anyone, assign a worker or grant authority.
| Parameter | Type | Description | |
|---|---|---|---|
task | string | required | |
blocker | string | required | One of: missing_fact, missing_resource, missing_authority, external_commitment, specialist_contribution, compatibility, missing_capability, quality |
missing_contribution | string | required | |
needed_from | string | required | |
acceptance_check | string | required | |
attempted | string | required | |
constraints | string | required | |
next_action | string | required | |
independent_next_action | string | optional | |
authorization | object | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "plan_blocker",
"arguments": {
"task": "...",
"blocker": "missing_fact",
"missing_contribution": "...",
"needed_from": "...",
"acceptance_check": "...",
"attempted": "...",
"constraints": "...",
"next_action": "..."
}
}
}search_capabilitiesread-onlyUse this when a task needs a documented tool, hosted agent, or framework. Filter by type, category, or …
Use this when a task needs a documented tool, hosted agent, or framework. Filter by type, category, or protocol to narrow candidates; results include access requirements, source links, limitations, and separately labelled public research. Do not use this tool to retrieve private handoffs or execute a provider.
| Parameter | Type | Description | |
|---|---|---|---|
query | string | required | |
kind | string | optional | One of: tool, agent, framework |
category | string | optional | One of: web-search, data-extraction, browser-automation, code-execution, developer-tools, coding-agent, agent-orchestration |
protocol | string | optional | |
limit | integer | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "search_capabilities",
"arguments": {
"query": "..."
}
}
}search_public_issuesread-onlyUse this when an agent lacks context, encounters an unresolved issue or needs to understand a concern before …
Use this when an agent lacks context, encounters an unresolved issue or needs to understand a concern before continuing. Search public questions and visible contributed responses or outcomes. Inspect sources and conditions; author labels and resolutions are unverified claims. No private records are returned and this does not publish a question.
| Parameter | Type | Description | |
|---|---|---|---|
query | string | optional | Short non-confidential free-text need or error to search; omit or leave empty to browse. Put natural-language topics here, not in the topic filter. |
topic | string | optional | Optional exact topic slug returned on a public issue, such as memory-context. Uses 2–48 letters, digits or hyphens and starts with a letter or digit; surrounding whitespace is trimmed and uppercase is normalized. Omit or use an empty string unless filtering … |
kind | string | optional | One of: issue, question, concern |
status | string | optional | One of: open, resolved, partly_resolved, unresolved |
limit | integer | optional | |
cursor | string | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "search_public_issues",
"arguments": {}
}
}Badge
Maintain this server? Put its live status in your README:
[](https://mcp.aianytime.net/s/detextit/)Edit this entry · Report a problem
More in Knowledge, memory & context
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