Directory / Agents, IDEs & developer tools
ComputeFirst
Catalog of versioned, deterministic tools for exact math, CSV and JSON transforms, date math, text, hashing and identifier checks; search, read the schema, then execute by id and version. Free, no account or API key. Endpoint: https://computefirst.net/mcp
Live Answered an MCP handshake without credentials and listed 15 tools.
- Category
- Agents, IDEs & developer tools
- Transport
http- Source
- https://computefirst.net/docs
- Endpoint
https://computefirst.net/mcp- MCP Registry
io.github.321zz321/computefirst- Reports itself as
- ComputeFirst 0.8.0
- Protocol
- 2025-06-18
- Tools
- 15
- Context cost
- about 2,124 tokens for the tool definitions (estimated at four characters per token)
- Tool definitions last changed
- no change seen since first check
- Handshake time
- 358 ms
- Last checked
- 2026-11-22 11:27:29 UTC
- Listed since
- 2026-11-18
Health and compatibility
| Endpoint reachable | Verified | Responded in 358 ms |
|---|---|---|
| MCP handshake (initialize) | Verified | Completed without credentials |
| Tool discovery (tools/list) | Verified | 15 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
5 daily checks so far; median response 358 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 computefirst https://computefirst.net/mcpClaude Desktop
Open Settings → Connectors → Add custom connector and paste this URL:
https://computefirst.net/mcpOr bridge it through mcp-remote in claude_desktop_config.json (needs Node.js):
{
"mcpServers": {
"computefirst": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://computefirst.net/mcp"
]
}
}
}Cursor
Or add it to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"computefirst": {
"url": "https://computefirst.net/mcp"
}
}
}VS Code
Or add it to .vscode/mcp.json:
{
"servers": {
"computefirst": {
"type": "http",
"url": "https://computefirst.net/mcp"
}
}
}Or from a terminal:
code --add-mcp '{"name": "computefirst", "type": "http", "url": "https://computefirst.net/mcp"}'Windsurf
Add it to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"computefirst": {
"serverUrl": "https://computefirst.net/mcp"
}
}
}Other clients
Most clients accept this shape. The endpoint is:
https://computefirst.net/mcp{
"mcpServers": {
"computefirst": {
"type": "http",
"url": "https://computefirst.net/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 15
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
activityread-onlyThe account's recent calls and outcomes; pass next as before for older ones. Without a key: signed_in:false.
The account's recent calls and outcomes; pass next as before for older ones. Without a key: signed_in:false.
| Parameter | Type | Description | |
|---|---|---|---|
limit | integer | optional | |
before | string | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "activity",
"arguments": {}
}
}describeread-onlyInput schema, limits and examples of one ComputeFirst catalog tool, by id and version.
Input schema, limits and examples of one ComputeFirst catalog tool, by id and version.
| Parameter | Type | Description | |
|---|---|---|---|
id | string | required | |
version | string | required |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "describe",
"arguments": {
"id": "...",
"version": "..."
}
}
}executeread-onlyRun one ComputeFirst catalog tool by id and version with its JSON input. Returns the deterministic result and …
Run one ComputeFirst catalog tool by id and version with its JSON input. Returns the deterministic result and an unmeasured savings receipt. Limits: computefirst.net/docs#limits.
| Parameter | Type | Description | |
|---|---|---|---|
id | string | required | |
version | string | required | |
input | object | required | |
model | string | optional | Optional: your model id, only so savings can be shown per model |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "execute",
"arguments": {
"id": "...",
"version": "...",
"input": {}
}
}
}execute_batchread-onlyRun 1–20 ComputeFirst catalog tools in one request. Optional bindings fill an input key from an earlier …
Run 1–20 ComputeFirst catalog tools in one request. Optional bindings fill an input key from an earlier result (JSON Pointer); include_result:false omits an intermediate. Steps after a failed dependency are skipped; nothing is retried automatically. Each success is one execution. Inputs, results and response: 256 KiB each. A factory work budget can skip an item with batch_work_limit; finance and exact decimal power/root/expression tools use the full factory allowance. Send additional factory operations separately. Split refused work; successful items are never retried automatically.
| Parameter | Type | Description | |
|---|---|---|---|
operations | object[] | required | |
model | string | optional | Optional: your model id, only so savings can be shown per model |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "execute_batch",
"arguments": {
"operations": []
}
}
}feedbackcan modifyTell ComputeFirst what helped or went wrong (a missing tool fits request_tool). A stable request_id makes …
Tell ComputeFirst what helped or went wrong (a missing tool fits request_tool). A stable request_id makes retries safe. Leave out secrets and raw data.
| Parameter | Type | Description | |
|---|---|---|---|
category | string | required | One of: missing_capability, useful, wrong_result, hard_to_use, other |
message | string | required | |
request_id | string | required | |
execution_ref | string | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "feedback",
"arguments": {
"category": "missing_capability",
"message": "...",
"request_id": "..."
}
}
}list_saved_toolsread-onlyTools saved in the account's library (id, version, note). Without a key: signed_in:false and no tools.
Tools saved in the account's library (id, version, note). Without a key: signed_in:false and no tools.
Takes no parameters.
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "list_saved_tools",
"arguments": {}
}
}profileread-onlyThe signed-in account: keys, privileges and tool-request status. Without a key: signed_in:false and the …
The signed-in account: keys, privileges and tool-request status. Without a key: signed_in:false and the optional extras.
Takes no parameters.
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "profile",
"arguments": {}
}
}remove_saved_toolcan modifydestructiveRemove a tool id and version from the account's library. Without a key nothing changes.
Remove a tool id and version from the account's library. Without a key nothing changes.
| Parameter | Type | Description | |
|---|---|---|---|
id | string | required | |
version | string | required |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "remove_saved_tool",
"arguments": {
"id": "...",
"version": "..."
}
}
}report_savingscan modifyOptional, for the person: your model id and, if known, your own estimate of the tokens a call saved …
Optional, for the person: your model id and, if known, your own estimate of the tokens a call saved (estimated_tokens_saved). Returns its dollar value at public list prices; unknown stays null. A measured comparison adds task_id, baseline_id, baseline, actual, whole_task:true, execution_ref.
| Parameter | Type | Description | |
|---|---|---|---|
model | string | required | |
provider | string | optional | |
execution_ref | string | optional | |
estimated_tokens_saved | object | optional | |
task_id | string | optional | |
baseline_id | string | optional | |
baseline | object | optional | |
actual | object | optional | |
whole_task | any | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "report_savings",
"arguments": {
"model": "..."
}
}
}request_toolcan modifyAsk for a tool that does not exist yet: the task, optionally example input and output. Optional contact_email …
Ask for a tool that does not exist yet: the task, optionally example input and output. Optional contact_email (with email_consent:true), only if the person wants one email when it ships. Leave out secrets.
| Parameter | Type | Description | |
|---|---|---|---|
description | string | required | |
example_input | string | optional | |
example_output | string | optional | |
contact_email | string | optional | |
email_consent | boolean | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "request_tool",
"arguments": {
"description": "..."
}
}
}save_toolcan modifySave a tool id and version to the account's library, with an optional note (saving again replaces the note). …
Save a tool id and version to the account's library, with an optional note (saving again replaces the note). Without a key nothing is saved.
| Parameter | Type | Description | |
|---|---|---|---|
id | string | required | |
version | string | required | |
note | string | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "save_tool",
"arguments": {
"id": "...",
"version": "..."
}
}
}savingsread-onlySavings totals, optionally for one model: with a key, the account's measured and estimated totals; otherwise …
Savings totals, optionally for one model: with a key, the account's measured and estimated totals; otherwise community verified totals. Unmeasured is not zero.
| Parameter | Type | Description | |
|---|---|---|---|
model | string | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "savings",
"arguments": {}
}
}searchread-onlySearch the ComputeFirst catalog (computefirst.net/tools) with an English task. Returns up to 5 tools (3 by …
Search the ComputeFirst catalog (computefirst.net/tools) with an English task. Returns up to 5 tools (3 by default) with id, version and a 0–1 score; a confident first match includes its input contract. No match: request_tool can ask for one.
| Parameter | Type | Description | |
|---|---|---|---|
query | string | required | |
limit | integer | optional | |
include_contract | boolean | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "search",
"arguments": {
"query": "..."
}
}
}sign_incan modifyOnly when the person explicitly asks for a free account (consent:true): creates one for their email …
Only when the person explicitly asks for a free account (consent:true): creates one for their email (unverified) and returns an agent key once, for saved tools, history, personal savings and a higher limit. The person stores the key in their client settings; do not repeat it in the conversation. newsletter:true only if they ask.
| Parameter | Type | Description | |
|---|---|---|---|
email | string | required | |
consent | any | required | |
newsletter | boolean | optional |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "sign_in",
"arguments": {
"email": "...",
"consent": "..."
}
}
}subscribecan modifySubscribe an email to new-tool announcements, only when the person asks for them (consent:true). Every email …
Subscribe an email to new-tool announcements, only when the person asks for them (consent:true). Every email has an unsubscribe link.
| Parameter | Type | Description | |
|---|---|---|---|
email | string | required | |
consent | any | required |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "subscribe",
"arguments": {
"email": "...",
"consent": "..."
}
}
}Badge
Maintain this server? Put its live status in your README:
[](https://mcp.aianytime.net/s/computefirst/)Edit this entry · Report a problem
More in Agents, IDEs & developer tools
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