Runitonai Mcp

io.github.StructLabs-io由 GitHub 帳號 StructLabs-io 發布v0.2.0更新於 Oct 25, 2026

Read-only MCP connector serving the Run It on AI book; index and Implementation Blocks are free.

已驗證Streamable HTTP可網頁執行效率與工作流知識與記憶

概覽

AI 產生的概覽

《Run It on AI》一書的唯讀配套伺服器,讓助理取得書籍索引、章節與 Implementation Block。

可以做什麼
透過 activate 載入配套助理的操作說明與參與模式,使用者尋求 AI 選型或導入協助時應先呼叫。列出所有章節與附錄的 ID 及其 Implementation Block 名稱,並依 slug 取得完整章節或指定小節。依章節與名稱取得結構化的 Implementation Block(讀者提示、代理備註、目標產物),無需憑證。章節搜尋、playbook、遙測與工作階段歷史等工具在 Phase 1 僅為未實作的佔位。
適用情境
適合《Run It on AI》的讀者,讓助理在討論 AI 導入時調取章節正文與練習內容;也適合不需購買即可瀏覽免費索引與 Implementation Block 的情境。
執行需求
遠端 streamable HTTP 端點,無需本機安裝。取得章節正文需要讀者以存取碼形式提供 Gumroad 授權金鑰;activate 說明與 Implementation Block 無需憑證。連線經由助理平台的雲端中转。
安裝前請注意
存取碼是標識購買紀錄的 Gumroad 授權金鑰,會傳送到伺服器、向 Gumroad 驗證並以雜湊形式快取一天;退款或停用的金鑰將失效。README 稱不會接收對話、檔案、姓名與電子郵件,工具呼叫由平台雲端看到,而非使用者機器直接連線。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Runitonai Mcp,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.StructLabs-io%2Frunitonai-mcp/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": {
    "runitonai": {
      "type": "http",
      "url": "https://mcp.runitonai.com/mcp"
    }
  }
}

README

Run It on AI — the companion server, in full

This repository is the complete source code of the server that powers the Run It on AI reading companion at mcp.runitonai.com. If you bought the book and connected your AI to it, this is everything that runs on our side.

We publish it so you do not have to take our word for anything. The server is a few hundred lines of TypeScript. You (or your AI — paste any file into it and ask) can read exactly what it does and, just as importantly, what it cannot do.

The short version

What reaches our server when you use the companion:

  • The name of the tool your AI called (for example "fetch chapter 3").
  • The chapter or exercise it asked for.
  • Your access code — the license key printed on your Gumroad receipt.

What never reaches us, because there is no code here that could receive, store, or forward it:

  • Your conversations with your AI.
  • Your files, documents, or anything on your machine.
  • Your name.
  • Your email. Search this repository for an email field: there is none. No tool, no endpoint, no code path accepts one.
  • The picture your AI forms of you while you work. That stays inside your AI, on your side.

Who talks to whom: when you add the companion as a Claude connector, your machine never contacts our server directly — Anthropic's cloud brokers the connection. On ChatGPT, OpenAI's cloud does. We see tool calls, not you.

How access works

Your credential is the license key on your Gumroad receipt (a code like XXXXXXXX-XXXXXXXX-XXXXXXXX-XXXXXXXX). It identifies a purchase, not a person. The server checks it against Gumroad, caches a hash of it for a day, and rate-limits it. Refunded or disabled keys stop working. See src/license.ts — the whole mechanism is one file.

Only chapter text needs the key. The companion's operating instructions (activate) and every Implementation Block — the book's working exercises — are served without any credential at all; the exercises are also published right here in implementation-blocks/.

Connect it

Claude (web or desktop) — the easy path. Settings -> Connectors -> Add custom connector, then paste:

https://mcp.runitonai.com/mcp

Start a chat with: Activate Run It on AI — my access code is <your license key>.

ChatGPT. Use the "Run It on AI Companion" GPT (link in the book), or build your own: create a Custom GPT and import https://mcp.runitonai.com/openapi.yaml as an Action.

Claude Code (terminal users).

sh
claude mcp add --transport http runitonai-book https://mcp.runitonai.com/mcp

Codex. In ~/.codex/config.toml:

toml
[mcp_servers.runitonai_book]url = "https://mcp.runitonai.com/mcp"

What is in this repo

PathWhat it is
src/worker.tsThe Cloudflare Worker: routing, transports, the Gumroad sync endpoint
src/license.tsLicense-key verification and caching (the access gate)
src/auth.tsVerification of legacy bearer tokens (nothing mints new ones)
src/rate_limit.tsPer-key rate limiting
src/mcp/MCP protocol plumbing (tool catalog, dispatch, transports)
src/tools/The tools your AI can call
openapi-v1.yamlThe same surface described for ChatGPT Actions
implementation-blocks/Every Implementation Block from the book, as readable markdown

Two data files ship as placeholders: src/data/chapters.json (the book's chapter text) and src/data/skill.json (the companion's operating instructions). Both are generated from the book manuscript at deploy time. The book's prose is the product, so it is not in the public repo — but the code that serves it is all here, and the Implementation Blocks (the working exercises) are published in full in implementation-blocks/.

Note for contributors: everything in this repo is generated from the private manuscript repo by a sync script, and a pre-commit hook there re-syncs it on every relevant change. The Implementation Blocks live in the book's manuscript; the copies here are build artifacts — never edit them here, they will be overwritten.

Run it yourself

sh
npm installnpm run typechecknpm run dev        # local server on localhost:8787

wrangler.toml ships with placeholder KV namespace ids; point them at your own Cloudflare account if you want to self-host the shell.

License

MIT — see LICENSE. The book itself (chapters, companion instructions) remains copyrighted content of StructLabs.io Pte Ltd and is not part of this repository.

來源:README.md,提交 d8fb21d

工具

11

activate

Start here. Returns the Run It on AI companion's full operating instructions (engagement modes, routing, voice rules, tool usage). Call this FIRST — before any other tool — when the user says "Activate Run It on AI", mentions the Run It on AI ebook, or asks for help choosing/deploying AI in their business. No authentication.

無需輸入參數。

list_book_index

Discovery: every valid chapter_id with its title — front matter, all chapters, AND all appendices (e.g. appendix-b-online-reference) — plus Implementation Block names per chapter. Call this whenever unsure which chapter_id to use. No authentication.

無需輸入參數。

lookup_chapter

Fetch a full chapter or a named section by slug — works for appendices too. Buyer-gated: pass the reader's access_code (their Gumroad license key). Unsure of the slug? Call list_book_index first.

輸入參數sectionchapter_id必填access_code

get_implementation_block

Fetch a structured Implementation Block (reader_prompt, agent_notes, target_artifact) by chapter and name. Free to call — no access code needed; the Implementation Blocks are public (they also ship in the open-source server repo).

輸入參數namechapter_id必填

find_section

Stub — not implemented in Phase 1. See tool response 'phase' field.

無需輸入參數。

find_playbook

Stub — not implemented in Phase 1. See tool response 'phase' field.

無需輸入參數。

get_playbook

Stub — not implemented in Phase 1. See tool response 'phase' field.

無需輸入參數。

report_telemetry

Stub — not implemented in Phase 1. See tool response 'phase' field.

無需輸入參數。

get_session_history

Stub — not implemented in Phase 1. See tool response 'phase' field.

無需輸入參數。

save_session_state

Stub — not implemented in Phase 1. See tool response 'phase' field.

無需輸入參數。

forget_session_history

Stub — not implemented in Phase 1. See tool response 'phase' field.

無需輸入參數。

版本歷史

1
  1. v0.2.0最新Sep 16, 2026

評分

已滿足適用檢查項的 75%

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

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 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