Skip to main content
Glama

web2mcp

Turn any website or REST API into MCP tools — one tiny Cloudflare Worker, zero dependencies.

English · 简体中文

CI License: MIT Runtime deps: 0 MCP

Deploy to Cloudflare

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 …

web2mcp demo: list tools, then call wikipedia_summary and currency_latest on the public demo

Try it in 30 seconds

No install, no account. A public demo runs at:

https://web2mcp.cwei59969.workers.dev/mcp

1. List the tools with the official MCP Inspector (CLI mode, works over SSH):

npx -y @modelcontextprotocol/inspector --cli https://web2mcp.cwei59969.workers.dev/mcp \
  --transport http --method tools/list

2. Call one:

npx -y @modelcontextprotocol/inspector --cli https://web2mcp.cwei59969.workers.dev/mcp \
  --transport http --method tools/call --tool-name wikipedia_summary --tool-arg title=Cloudflare

Or with plain curl:

curl -s https://web2mcp.cwei59969.workers.dev/mcp \
  -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"weather_forecast","arguments":{"latitude":35.68,"longitude":139.69}}}'

Prefer a UI? Run npx @modelcontextprotocol/inspector, pick Streamable HTTP, paste the URL.

The demo runs on the Workers free plan: it is rate-limited, reader_read is disabled, bilibili_* is not available (Bilibili blocks Cloudflare IPs), and the github_* tools often hit GitHub's anonymous rate limit (HTTP 403). Deploy your own, or run it locally, for real use.

Related MCP server: Remote MCP Server Authless

Who is this for

  • You want an agent to use a public REST API today and don't want to write an MCP server for it. Describe the endpoint in ~15 lines of config; web2mcp turns it into a typed MCP tool.

  • You have a big API (hundreds of endpoints) and tool definitions are eating your context. Catalog mode exposes it as 2 tools (search_api + call_api).

  • You want free, always-on hosting with no servers: one Cloudflare Worker, zero runtime dependencies.

  • You want to run it locally with no cloud account: npx -y github:charleswei118/web2mcp (stdio).

Not a fit if you need browser automation / logged-in scraping, or OAuth on behalf of end users.

Why

  • Config, not code. A connector is a plain object: base URL, path, query, params. No SDK to learn.

  • Zero runtime dependencies. ~800 lines of readable JavaScript. Audit it in 10 minutes.

  • Token-friendly output. pick and fields trim giant JSON responses down to what the model needs.

  • Free hosting. Runs on the Cloudflare Workers free plan. Deploy in one click.

  • Safe by default. Requests are locked to each connector's host, arguments are type-checked, secrets stay server-side, optional bearer auth.

  • OpenAPI import. Convert any OpenAPI 3 spec into a connector with one command.

Built-in connectors (no API keys)

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)

Deploy your own in one click

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.<your-subdomain>.workers.dev/mcp, and every push to your copy redeploys it. The free Workers plan is enough.

Quick start

git clone https://github.com/charleswei118/web2mcp && cd web2mcp
npm test                 # unit tests, no install needed (Node 20+)
npm run smoke            # calls the built-in tools against the real APIs
npx wrangler dev         # local server at http://localhost:8787/mcp (no Cloudflare login needed)
npx wrangler deploy      # your own https://web2mcp.<you>.workers.dev/mcp

wrangler dev serves /mcp without auth unless you create .dev.vars: cp .dev.vars.example .dev.vars and set AUTH_TOKEN.

Optional: protect your deployed endpoint

npx wrangler secret put AUTH_TOKEN

Connect your client

Use the demo URL to try it; swap in https://web2mcp.<you>.workers.dev/mcp once you deploy. The demo needs no token. Add the Authorization header only if you set AUTH_TOKEN on your own deployment.

Claude Code

claude mcp add --transport http web2mcp https://web2mcp.cwei59969.workers.dev/mcp
# your own, protected deployment:
claude mcp add --transport http web2mcp https://web2mcp.<you>.workers.dev/mcp \
  --header "Authorization: Bearer $WEB2MCP_TOKEN"

Cursor (~/.cursor/mcp.json, remote URL supported natively)

{
  "mcpServers": {
    "web2mcp": { "url": "https://web2mcp.cwei59969.workers.dev/mcp" }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "web2mcp": { "type": "http", "url": "https://web2mcp.cwei59969.workers.dev/mcp" }
  }
}

Claude Desktop / Windsurf / any stdio-only client (bridge with mcp-remote)

{
  "mcpServers": {
    "web2mcp": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://web2mcp.cwei59969.workers.dev/mcp"]
    }
  }
}

With a protected deployment, add the header:

"args": ["-y", "mcp-remote", "https://web2mcp.<you>.workers.dev/mcp",
         "--header", "Authorization: Bearer ${WEB2MCP_TOKEN}"],
"env": { "WEB2MCP_TOKEN": "your-token" }

No cloud at all: run it locally over stdio

{
  "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).

Claude.ai / ChatGPT connectors / OpenAI Responses API / Cloudflare AI Playground: paste the URL directly.

Write a connector

Create connectors/myapi.js and add it to connectors/index.js:

export default {
  name: "openlibrary",                       // tool names become openlibrary_<tool>
  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.

From an OpenAPI spec

node scripts/openapi2connector.js https://petstore3.swagger.io/api/v3/openapi.json petstore --only GET > connectors/petstore.js

Catalog mode: 665 endpoints, 2 tools

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 schemas

  • call_api — run one operation by name with an arguments object

Measured 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.

Endpoints

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.

Roadmap

  • Catalog mode (search_api + call_api) — v0.2

  • Load OpenAPI specs at runtime from a URL

  • One-click “Deploy to Cloudflare” — v0.2

  • HTML scraping connectors (CSS selectors via HTMLRewriter)

  • Per-tool rate limits and KV caching

  • OAuth for connectors that need user accounts

  • Connector registry: share connectors as JSON files

  • Agent-to-agent (A2A) chat rooms on Durable Objects

PRs with new connectors are very welcome — see CONTRIBUTING.md.

Troubleshooting

You see

Why

Fix

{"error":"Use POST for MCP requests"} (HTTP 405)

You opened /mcp in a browser or sent GET

MCP clients POST to /mcp. Open / for the human-readable tool list.

HTTP 401 on /mcp

AUTH_TOKEN is set on the deployment

Send Authorization: Bearer <token> (see client configs above).

Upstream 403 Forbidden: API rate limit exceeded from github_*

GitHub's anonymous limit, shared by all Cloudflare IPs

npx wrangler secret put GITHUB_TOKEN on your deployment, or run locally.

Unknown tool: <name> (JSON-RPC -32602)

Tool not enabled (ENABLED_CONNECTORS), disabled on the demo, or the name is wrong

Run tools/list first; check ENABLED_CONNECTORS.

bilibili_* fails on Workers

Bilibili blocks Cloudflare IPs

Use stdio / Docker / self-hosted Node.

reader_read missing on the demo

Disabled on the public demo to prevent abuse

Deploy your own.

reader_read rejects a URL

SSRF guard: localhost, private IPs, metadata hosts and odd ports are refused

Use a public http(s) URL.

Response cut off

MAX_OUTPUT_CHARS (default 20000)

Raise it, or use pick / fields in the connector.

wrangler: Proxy environment variables detected

You're behind HTTP(S)_PROXY

Harmless; wrangler uses the proxy for upstream fetches.

npm test syntax errors

Node < 20

Upgrade to Node 20+.

Responsible use

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.

License

MIT

If web2mcp saves you time, please ⭐ the repo — it helps others find it.

Available Tools

13 tools
currency_latestFrankfurter exchange rates: latestA
Read-only
Inspect

[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.

Inputs: base, symbols.

github_repoGitHub: repoA
Read-only
Inspect

[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.

Inputs: repo (required), owner (required).

github_search_reposGitHub: search_reposA
Read-only
Inspect

[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, language, url, updated_at). Unauthenticated calls share a low rate limit.

Inputs: query (required), sort, limit.

hackernews_front_pageHacker News: front_pageA
Read-only
Inspect

[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.

Inputs: limit.

npm_packagenpm: packageA
Read-only
Inspect

[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.

Inputs: name (required).

npmstats_downloadsnpm stats: downloadsA
Read-only
Inspect

[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.

Inputs: name (required).

reader_readWeb reader: readA
Read-only
Inspect

[reader] Fetch any public web page and return its main content as Markdown, with navigation and ads stripped. Use it as a fallback for sites without a dedicated tool (prefer wikipedia_summary, github_repo etc. when they fit). Pages behind logins or paywalls may come back empty; long pages are truncated.

Inputs: url (required).

weather_forecastOpen-Meteo Weather: forecastA
Read-only
Inspect

[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 location's local timezone.

Inputs: latitude (required), longitude (required), days.

wikipedia_summaryWikipedia: summaryA
Read-only
Inspect

[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.

Inputs: title (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 13 tools

    Disambiguation5/5

    Each tool is tied to a distinct source and operation, with clear distinctions between search vs retrieval tools such as wikipedia_search/wikipedia_summary, hackernews_front_page/hackernews_search, and github_search_repos/github_repo. reader_read is explicitly positioned as a fallback, so it does not create meaningful ambiguity.

    Naming Consistency4/5

    Tool names consistently use snake_case with service/source prefixes, making the set easy to scan. There are minor deviations such as noun-only names like npm_package and github_repo, plus the separate npmstats namespace, but the convention remains predictable.

    Tool Count5/5

    With 13 tools spanning several lightweight web data sources, the count is well within a reasonable range and each tool has a clear role. There is no obvious bloat or duplicate operation.

    Completeness4/5

    The surface covers the core read paths for each included source and provides a generic reader_read fallback for arbitrary pages. Some gaps exist, such as HN item/comment retrieval, GitHub code/issues/PRs, currency conversion/history, npm search, and a general web search tool, but agents can often work around them via the reader or dedicated tools where provided.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers