GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者提供的说明(英文原文)
Zero-dependency Cloudflare Worker gateway turning websites and REST APIs into MCP tools.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://web2mcp.cwei59969.workers.dev/mcp在终端中运行这条命令
claude mcp add --transport http web2mcp https://web2mcp.cwei59969.workers.dev/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"web2mcp": {
"url": "https://web2mcp.cwei59969.workers.dev/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"web2mcp": {
"type": "http",
"url": "https://web2mcp.cwei59969.workers.dev/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://web2mcp.cwei59969.workers.dev/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
工具名称和描述与服务器在 2026年11月6日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
wikipedia_search[wikipedia] Full-text search of English Wikipedia. Use this to find the right article title, then call wikipedia_summary with it. Returns titles, short descriptions and excerpts, best match first.
wikipedia_summary[wikipedia] Get the lead summary of an English Wikipedia article by its exact title (redirects are followed). If you are unsure of the title, use wikipedia_search first. Returns title, short description, the lead extract and the article url.
hackernews_front_page[hackernews] List the stories currently on the Hacker News front page, ranked as on the site. Use this to see what is trending now; use hackernews_search to find stories on a topic. Returns title, url, points, comment count and story id.
hackernews_search[hackernews] Full-text search of Hacker News stories (not comments) by keyword, ranked by relevance. Use this to find discussions about a product, project or topic; use hackernews_front_page for what is trending now. Returns title, url, points, comment count, date and story id.
geocode_search[geocode] Turn a city or place name into coordinates. Use this before weather_forecast, which needs latitude/longitude. A name can match several places, so up to `limit` candidates are returned, best match first, each with name, country, region, latitude, longitude and timezone.
weather_forecast[weather] Get current conditions and a daily forecast for a location given by coordinates. If you only have a place name, call geocode_search first. Returns temperature (°C), humidity, wind (km/h), WMO weather code, and per-day max/min temperature and precipitation (mm) in the lo
currency_latest[currency] Get the latest European Central Bank reference exchange rates (updated once per working day) from a base currency. Omit symbols to get all ~30 currencies. Returns an object with base, date and a rates map, e.g. rates.CNY.
github_search_repos[github] Find public GitHub repositories matching a query. Use this when you don't know the exact repo; use github_repo when you already have owner and name. Supports GitHub qualifiers like 'mcp language:rust stars:>100'. Returns up to `limit` repos (full_name, description, stars
github_repo[github] Get metadata for one public repository you already know by owner and name: description, stars, forks, language, license, topics, url and last push time. Use github_search_repos first if you only have keywords. Returns an error if the repo does not exist or is private.
npm_package[npm] Get the latest version, description, license and homepage of an npm package. For download counts use npmstats_downloads instead. Returns an error if the package does not exist.
npmstats_downloads[npmstats] Get how many times an npm package was downloaded in the last 7 days, as a popularity signal. For version or license info use npm_package instead. Returns package, downloads, start and end dates.
arxiv_search[arxiv] Search arXiv research papers by keyword across title, abstract and authors, ranked by relevance. Use it for academic preprints; use wikipedia_search for general background. Returns id/link, title, publication date, authors and abstract.
holidaycn_year[holidaycn] List every official holiday day off and every make-up workday (调休上班) in mainland China for one year, e.g. to tell whether a date is a working day or plan around 春节/国庆. Returns entries of name (Chinese holiday name), date (YYYY-MM-DD) and isOffDay (true = day off, fals
baiduhot_realtime[baiduhot] Get the current Baidu real-time hot search ranking (百度热搜榜): what Chinese internet users are searching for right now. Use it for Chinese news and trending topics; use hackernews_front_page for English tech news. Returns up to 50 entries of word (topic in Chinese), index
shici_random[shici] Get one random famous line of classical Chinese poetry (诗/词/曲), optionally from a theme. Use it for a daily quote, a greeting card line or a writing prompt. Returns content (the line), origin (poem title), author and category (theme path such as 古诗文-抒情-感恩).
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 charleswei118 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
在 54 毫秒内响应(HTTP 200)
无需登录
已读取 15 个工具描述,未发现针对 AI 的隐藏指令
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(0.2.0)于7天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:GitHub, Desktop Commander, Cloudflare MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Turn any website or REST API into MCP tools — one tiny Cloudflare Worker, zero dependencies.
English · 简体中文
GitHub's 665 REST endpoints → 2 MCP tools, ~147,000 tokens of tool definitions → ~300 (catalog mode)
Every AI agent (Claude, ChatGPT, Cursor, your own bots…) now speaks the Model Context Protocol. But most websites and apps don't. web2mcp is the glue: describe an HTTP API in a few lines of config and it instantly becomes an MCP tool that any agent can call — hosted for free on Cloudflare's edge.
Claude / Cursor / any MCP client
│ MCP (Streamable HTTP, JSON-RPC) ▼ ┌──────────────────────────┐ │ web2mcp (CF Worker) │ connectors/*.js or CONNECTORS_JSON └──────────────────────────┘ │ │ │ Wikipedia GitHub any REST API / web page …
A public demo is running at https://web2mcp.cwei59969.workers.dev (tool list) with the MCP endpoint at:
https://web2mcp.cwei59969.workers.dev/mcp
Paste it into any client that supports remote MCP servers, or:
curl -s https://web2mcp.cwei59969.workers.dev/mcp -H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"weather_forecast","arguments":{"latitude":35.68,"longitude":139.69}}}'
The demo is rate-limited by the free plan and has reader_read disabled. Deploy your own for real use.
pick and fields trim giant JSON responses down to what the model needs.| Tool | What it does |
|---|---|
wikipedia_search, wikipedia_summary | Search Wikipedia, read article summaries |
hackernews_front_page, hackernews_search | Hacker News stories |
geocode_search | Place name → coordinates (Open-Meteo) |
weather_forecast | Current weather + daily forecast (Open-Meteo) |
currency_latest | ECB exchange rates (Frankfurter) |
github_search_repos, github_repo | Public GitHub repositories (set GITHUB_TOKEN on Workers: shared IPs hit GitHub's anonymous limit) |
reader_read | Any web page → clean Markdown (Jina Reader) |
npm_package, npmstats_downloads | npm package info and weekly downloads |
arxiv_search | Search arXiv research papers |
holidays_list | Public holidays by country and year (Nager.Date) |
holidaycn_year | Mainland China holidays and make-up workdays (调休) for a year |
baiduhot_realtime | Baidu real-time hot search (百度热搜) |
shici_random | A random line of classical Chinese poetry (今日诗词) |
bilibili_popular, bilibili_ranking | Bilibili trending / ranking videos (stdio & self-hosted only: Bilibili blocks Cloudflare IPs) |
Click Deploy to Cloudflare above. Cloudflare copies this repo into your GitHub account, asks for an AUTH_TOKEN (any long random string, e.g. openssl rand -hex 32), then builds and deploys it. A minute later your server is live at https://web2mcp. .workers.dev/mcp, and every push to your copy redeploys it. The free Workers plan is enough.
git clone https://github.com/charleswei118/web2mcp && cd web2mcp
npm test # unit tests, no install needed (Node 20+) npm run smoke # calls every built-in tool against the real APIs npx wrangler dev # local server at http://localhost:8787/mcp npx wrangler deploy # your own https://web2mcp. .workers.dev/mcp
Optional: protect your endpoint
npx wrangler secret put AUTH_TOKEN
Claude Desktop / Cursor / Windsurf (via mcp-remote):
{
"mcpServers": { "web2mcp": { "command": "npx", "args": ["-y", "mcp-remote", "https://web2mcp. .workers.dev/mcp", "--header", "Authorization: Bearer ${WEB2MCP_TOKEN}"], "env": { "WEB2MCP_TOKEN": "your-token" } } } }
Run locally over stdio (no Cloudflare account needed; same connectors):
{
"mcpServers": { "web2mcp": { "command": "npx", "args": ["-y", "github:charleswei118/web2mcp"], "env": { "ENABLED_CONNECTORS": "wikipedia,hackernews,weather" } } } }
Or with Docker: docker build -t web2mcp . && docker run -i --rm web2mcp. Environment variables work the same as Worker bindings (ENABLED_CONNECTORS, CONNECTORS_JSON, MAX_OUTPUT_CHARS, TOOL_MODE=catalog).
Clients that support remote MCP servers natively (Claude.ai custom connectors, ChatGPT connectors, the OpenAI Responses API, Cloudflare AI Playground…) can use the URL directly. Test with the official inspector:
npx @modelcontextprotocol/inspector # transport: Streamable HTTP, URL: .../mcp
Create connectors/myapi.js and add it to connectors/index.js:
export default {
name: "openlibrary", // tool names become openlibrary_ description: "Search books on Open Library.", baseUrl: "https://openlibrary.org", headers: { /* "authorization": "Bearer ${MY_API_KEY}" */ }, tools: [ { name: "search", description: "Search books by title or author.", method: "GET", // GET | POST | PUT | PATCH | DELETE path: "/search.json", // "{arg}" in the path is URL-encoded query: { q: "{query}", limit: "{limit}" }, params: { query: { type: "string", required: true, description: "Title or author" }, limit: { type: "integer", minimum: 1, maximum: 20, default: 5 }, }, pick: "docs", // dotted path into the JSON response fields: ["title", "author=author_name", "year=first_publish_year"], }, ], };
Template rules:
| Syntax | Meaning |
|---|---|
"{arg}" | Tool argument. As a whole value it keeps its type; missing optional args are dropped. |
"${SECRET}" | Read from a Worker secret / var — never exposed to the model. |
"${?SECRET}" | Optional secret: the value is dropped when it is not set. |
pick: "a.b.*.c" | Select part of the response (* maps over arrays; a single value counts as a one-item list). |
fields: ["x", "alias=deep.path"] | Keep only these fields. |
limit: 10 | Truncate arrays. |
format: "public-url" (on a param) | Reject localhost, private/intranet IPs, cloud metadata, embedded credentials and odd ports before any request is made (SSRF guard). Used by reader_read. |
response: "xml" | Parse an XML/Atom/RSS response into JSON first, so pick / fields work on it (attributes become @name, namespace prefixes are dropped, repeated elements become arrays). Also "json", "text" (raw body) or "auto" (default). |
No-code option: put connectors in the CONNECTORS_JSON secret (a JSON array of the same objects) and they appear without touching the code. Use ENABLED_CONNECTORS="wikipedia,weather" to expose only some.
node scripts/openapi2connector.js https://petstore3.swagger.io/api/v3/openapi.json petstore --only GET > connectors/petstore.js
Exposing every endpoint as its own tool floods the model's context. In catalog mode web2mcp exposes just two tools:
search_api — find operations by keywords; returns their names and argument schemascall_api — run one operation by name with an arguments objectMeasured with GitHub's full REST OpenAPI spec (GET operations only, converted with scripts/openapi2connector.js):
| Mode | Tools in tools/list | Approx. context |
|---|---|---|
| Default (one tool per endpoint) | 665 | ~147,000 tokens |
| Catalog | 2 | ~300 tokens |
Turn it on per request with /mcp?mode=catalog, or for the whole deployment with the variable TOOL_MODE = "catalog" (?mode=tools switches back). Try it on the demo: https://web2mcp.cwei59969.workers.dev/mcp?mode=catalog.
| Path | |
|---|---|
POST /mcp | MCP Streamable HTTP endpoint (JSON responses, batch supported) |
POST /mcp?mode=catalog | Same, in catalog mode (search_api + call_api) |
GET / | Human-readable list of tools |
GET /tools | Tool list as JSON |
GET /health | Health check |
Supported MCP methods: initialize, ping, tools/list, tools/call, plus empty resources/list and prompts/list. Protocol versions 2025-06-18, 2025-03-26, 2024-11-05.
search_api + call_api) — v0.2HTMLRewriter)PRs with new connectors are very welcome — see CONTRIBUTING.md.
Only connect APIs and sites you are allowed to use. Respect each service's terms, robots rules and rate limits, and keep credentials in Worker secrets.
MIT
If web2mcp saves you time, please ⭐ the repo — it helps others find it.