io.github.321zz321Published by GitHub account 321zz321v1.0.0Updated Oct 24, 2026
Free deterministic tools for math, data transforms, dates, text, statistics, finance, and units.
Remote MCP server giving assistants a catalog of free deterministic tools for math, data transforms, dates, text, statistics, finance and units, run by id and…
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.321zz321%2Fcomputefirst/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"computefirst": {
"type": "http",
"url": "https://computefirst.net/mcp"
}
}
}Instructions for Claude Code, Codex, Grok, and other autonomous agents to use ComputeFirst for deterministic computation: search → read the versioned contract → execute. Free, no API key or sign-up. Live-verified catalog: 837 tools (2026-11-05).
Install the Claude Code skill and MCP connection from this repository's marketplace:
Or add the MCP connection alone:
Codex ~/.codex/config.toml:
For Codex skill discovery, copy skills/computefirst/ into .agents/skills/computefirst/ or ~/.agents/skills/computefirst/, preserving references. Client setup and sources cover Claude Code, Cursor, VS Code, generic MCP clients, and plain HTTP.
Read the skill for selection rules, exact requests, limits, and six actual API results. AGENTS.md provides condensed guidance. The full MCP route exposes gateway tools; /mcp/chatgpt offers 40 named operations with smaller limits.
Verify with Node.js 22+ and network access:
The script reads the documented requests/results directly and fails on drift. It also checks discovery and both MCP routes. No dependencies, credentials, or reporting calls. MIT license.
Source: README.md at commit 42bb834
Search tools
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.
limitqueryrequiredinclude_contractDescribe a tool
Input schema, limits and examples of one ComputeFirst catalog tool, by id and version.
idrequiredversionrequiredRun a tool
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.
idrequiredinputrequiredmodelversionrequiredRun tools in one batch
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.
modeloperationsrequiredRead savings
Savings totals, optionally for one model: with a key, the account's measured and estimated totals; otherwise community verified totals. Unmeasured is not zero.
modelSend feedback
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.
messagerequiredcategoryrequiredrequest_idrequiredexecution_refRequest a missing tool
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.
descriptionrequiredcontact_emailemail_consentexample_inputexample_outputSubscribe to new-tool emails
Subscribe an email to new-tool announcements, only when the person asks for them (consent:true). Every email has an unsubscribe link.
emailrequiredconsentrequiredCreate a free account (optional)
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.
emailrequiredconsentrequirednewsletterShow account profile
The signed-in account: keys, privileges and tool-request status. Without a key: signed_in:false and the optional extras.
Takes no parameters.
Show account activity
The account's recent calls and outcomes; pass next as before for older ones. Without a key: signed_in:false.
limitbeforeList saved tools
Tools saved in the account's library (id, version, note). Without a key: signed_in:false and no tools.
Takes no parameters.
Save a tool
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.
idrequirednoteversionrequiredRemove a saved tool
Remove a tool id and version from the account's library. Without a key nothing changes.
idrequiredversionrequiredReport model and savings (optional)
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.
modelrequiredactualtask_idbaselineproviderwhole_taskbaseline_idexecution_refestimated_tokens_saved100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
/plugin marketplace add 321zz321/computefirst-skill/plugin install computefirst@computefirstclaude mcp add --transport http computefirst https://computefirst.net/mcp[mcp_servers.computefirst]url = "https://computefirst.net/mcp"node scripts/verify-examples.mjs