ComputeFirst

io.github.321zz321由 GitHub 帳號 321zz321 發布v1.0.0更新於 Oct 24, 2026

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

已驗證Streamable HTTP可網頁執行開發者工具資料與分析

概覽

AI 產生的概覽

遠端 MCP 伺服器,為助理提供免費的決定性工具目錄,涵蓋數學、資料轉換、日期、文字、統計、金融與單位換算,依 id 與版本執行。

可以做什麼
  • 用英文任務描述搜尋目錄,取得排序後的工具 id、版本與符合分數
  • 呼叫前查看某個工具的輸入結構、限制與範例
  • 執行單一工具,或在一次請求中批次執行 1–20 個工具,並可用綁定把前一步結果填入後續輸入
  • 查看節省統計、回報自己的 token 節省估算,以及送出意見或申請尚不存在的工具
  • 管理可選的免費帳號:登入、查看個人資料與呼叫紀錄、儲存、列出與移除收藏工具
  • 在使用者明確要求時訂閱新工具郵件通知
適用情境
當助理需要精確、可重複的計算時適用,例如單位換算、日期運算、文字與資料轉換、統計,而不是憑估計作答。也適合把多個小的決定性步驟合併成一次批次呼叫。
執行需求
透過 streamable HTTP 連線到 computefirst.net 的遠端 MCP 端點;基本使用不需 API 金鑰或註冊。可選的免費帳號金鑰可解鎖收藏工具、歷史紀錄、個人節省統計與較高額度。README 中的驗證腳本需要 Node.js 22+ 與網路存取。
安裝前請注意
執行工具與批次任務會在遠端進行運算並把輸入傳送給第三方;意見回饋、工具申請與訂閱會把文字以及可選的電子郵件傳送給 ComputeFirst。登入會為該電子郵件建立帳號並一次性回傳 agent 金鑰,應存放在用戶端設定中,不要在對話裡重複。郵件訂閱與聯絡需要明確同意。不要在意見回饋或工具申請中傳送機密或原始資料。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 ComputeFirst,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.321zz321%2Fcomputefirst/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "computefirst": {
      "type": "http",
      "url": "https://computefirst.net/mcp"
    }
  }
}

README

ComputeFirst agent skill

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:

text
/plugin marketplace add 321zz321/computefirst-skill/plugin install computefirst@computefirst

Or add the MCP connection alone:

sh
claude mcp add --transport http computefirst https://computefirst.net/mcp

Codex ~/.codex/config.toml:

toml
[mcp_servers.computefirst]url = "https://computefirst.net/mcp"

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:

sh
node scripts/verify-examples.mjs

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.

來源:README.md,提交 42bb834

工具

15

describe

Describe a tool

Input schema, limits and examples of one ComputeFirst catalog tool, by id and version.

輸入參數id必填version必填

execute

Run 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.

輸入參數id必填input必填modelversion必填

execute_batch

Run 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.

輸入參數modeloperations必填

savings

Read 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.

輸入參數model

feedback

Send 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.

輸入參數message必填category必填request_id必填execution_ref

request_tool

Request 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.

輸入參數description必填contact_emailemail_consentexample_inputexample_output

subscribe

Subscribe 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.

輸入參數email必填consent必填

sign_in

Create 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.

輸入參數email必填consent必填newsletter

profile

Show account profile

The signed-in account: keys, privileges and tool-request status. Without a key: signed_in:false and the optional extras.

無需輸入參數。

activity

Show account activity

The account's recent calls and outcomes; pass next as before for older ones. Without a key: signed_in:false.

輸入參數limitbefore

list_saved_tools

List saved tools

Tools saved in the account's library (id, version, note). Without a key: signed_in:false and no tools.

無需輸入參數。

save_tool

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.

輸入參數id必填noteversion必填

remove_saved_tool

Remove a saved tool

Remove a tool id and version from the account's library. Without a key nothing changes.

輸入參數id必填version必填

report_savings

Report 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.

輸入參數model必填actualtask_idbaselineproviderwhole_taskbaseline_idexecution_refestimated_tokens_saved

版本歷史

1
  1. v1.0.0最新Oct 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分