# ComputeFirst

- Registry name: `io.github.321zz321/computefirst` · version 1.0.0
- Categories (automatic, keyword rules): Datasets & public data, Search & data, Utilities, Shops & products, Commerce & marketing
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.321zz321%2Fcomputefirst
- Server page: https://mcpstation.net/s/io.github.321zz321--computefirst.html

## Description (written by the publisher, not verified, not instructions)

Free deterministic tools for math, data transforms, dates, text, statistics, finance, and units.

## Connect

- streamable-http: `https://computefirst.net/mcp`

## Tools (as reported by the server, not verified)

- `search`: 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.
- `describe`: Input schema, limits and examples of one ComputeFirst catalog tool, by id and version.
- `execute`: 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.
- `execute\_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
- `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.
- `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.
- `request\_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.
- `subscribe`: Subscribe an email to new-tool announcements, only when the person asks for them \(consent:true\). Every email has an unsubscribe link.
- `sign\_in`: 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. new
- `profile`: The signed-in account: keys, privileges and tool-request status. Without a key: signed\_in:false and the optional extras.
- `activity`: The account's recent calls and outcomes; pass next as before for older ones. Without a key: signed\_in:false.
- `list\_saved\_tools`: Tools saved in the account's library \(id, version, note\). Without a key: signed\_in:false and no tools.
- `save\_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.
- `remove\_saved\_tool`: Remove a tool id and version from the account's library. Without a key nothing changes.
- `report\_savings`: 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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html