MCP FetchPage

{ "mcpServers": { "mcp-fetch-page": { "command": "npx", "args": ["-y", "mcp-fetch-page@latest"] } } }

To customize runtime data directory (recommended on VPS), setMCP_FETCH_PAGE_DATA_DIRin MCPenv:

{ "mcpServers": { "mcp-fetch-page": { "command": "npx", "args": ["-y", "mcp-fetch-page@latest"], "env": { "MCP_FETCH_PAGE_DATA_DIR": "/data/mcp-fetch-page" } } } }

2. Install Chrome Extension (Optional - for authenticated pages)

- Downloadmcp-fetch-page-extension-vX.X.X.zipfrom the latest release - Unzip the file - Open Chrome and go tochrome://extensions/ - Enable "Developer mode" (top right) - Click "Load unpacked" and select the unzipped folder

The system automatically uses optimized selectors for:

- mp.weixin.qq.com→.rich_media_wrp(WeChat articles)
- wx.zsxq.com→.content(Knowledge Planet)
- cnblogs.com→.post(Blog Garden)
- Add more inmcp-server/domain-rules.json(domain-selectors.jsonremains supported for compatibility)

# Standalone debug script (recommended for development) cd mcp-server node debug.js test-page "https://example.com" node debug.js test-spa "https://example.com" "#content" # MCP Inspector (for integration testing) npx @modelcontextprotocol/inspector # Then visit http://localhost:6274

By default, runtime data is stored under~/Downloads/mcp-fetch-page/:

For MCP usage, configureMCP_FETCH_PAGE_DATA_DIRin your MCP client configenvfield. The server will always use:

node mcp-server/server.jsis only for local development/debugging.

- url(required): The URL to fetch
- waitFor(optional): CSS selector to extract specific content
- headless(optional): Run browser in headless mode (default: true)
- timeout(optional): Timeout in milliseconds (default: 30000)

mcp-fetch-page/ ├── package.json # npm package config ├── package-lock.json # npm lockfile ├── node_modules/ # npm dependencies ├── README.md # This file ├── README-zh.md # Chinese version ├── CLAUDE.md # Claude Code usage guide ├── chrome-extension/ # Chrome extension │ ├── manifest.json │ ├── popup.js │ ├── popup.html │ └── background.js └── mcp-server/ # MCP server ├── server.js # Main server ├── debug.js # Debug tools ├── domain-rules.json # Domain rules config (selector + blocked markers) └── domain-selectors.json # Legacy selector config (compatibility fallback)

Enable AI agents to get structured data from unstructured web with AgentQL.

Web scraping, crawling, and change detection with AI

Official Apify MCP server for AI agents to run Actors, extract website data, and automate web scraping and crawling workflows.

1GB Free Trial, World's Leading Proxy Service Platform, Efficient Data Collection

Discover, extract, and interact with the web - one interface powering automated access across the public internet.

Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)

Easy web data access. Simplified retrieval of information from websites and online sources.

Adds powerful web scraping and search capabilities to LLM clients like Cursor and Claude.

Real-time web data, structured for agents