MCP Fetch Page
Fetches and extracts content from WeChat articles (mp.weixin.qq.com) with automatic CSS selector optimization for article content.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Fetch Page fetchpage(url="https://example.com", waitFor=".article-content")"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Fetch Page
Browser-based web page fetching with automatic cookie support and CSS selector extraction.
Features
π€ Browser Automation: Full JavaScript rendering with Puppeteer
πͺ Automatic Cookie Management: Loads all saved cookies automatically
π― CSS Selector Support: Extract specific content with selectors
π Domain Presets: Built-in selectors for common websites
π± SPA Support: Fully supports dynamic content and AJAX
Related MCP server: Fetch MCP Server
Quick Start
1. Configure MCP Server
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"mcp-fetch-page": {
"command": "npx",
"args": ["-y", "mcp-fetch-page@latest"]
}
}
}To customize runtime data directory (recommended on VPS), set MCP_FETCH_PAGE_DATA_DIR in MCP env:
{
"mcpServers": {
"mcp-fetch-page": {
"command": "npx",
"args": ["-y", "mcp-fetch-page@latest"],
"env": {
"MCP_FETCH_PAGE_DATA_DIR": "/data/mcp-fetch-page"
}
}
}
}Restart Claude Desktop.
2. Install Chrome Extension (Optional - for authenticated pages)
Download and install the Chrome extension to save cookies from authenticated sessions:
π₯ Download Extension from Releases
Installation steps:
Download
mcp-fetch-page-extension-vX.X.X.zipfrom the latest releaseUnzip the file
Open Chrome and go to
chrome://extensions/Enable "Developer mode" (top right)
Click "Load unpacked" and select the unzipped folder
Usage
Basic Usage
Login to a website in Chrome
Click the "Fetch Page MCP Tools" extension icon
Click "Save Cookies" button
Use in Claude/Cursor:
fetchpage(url="https://example.com")
Advanced Usage
// Basic fetching with automatic cookie loading
fetchpage(url="https://example.com")
// Extract specific content with CSS selector
fetchpage(url="https://example.com", waitFor="#main-content")
// WeChat articles (automatic selector)
fetchpage(url="https://mp.weixin.qq.com/s/xxxxx")
// Run in non-headless mode for debugging
fetchpage(url="https://example.com", headless=false)Domain Presets
The system automatically uses optimized selectors for:
mp.weixin.qq.com β
.rich_media_wrp(WeChat articles)wx.zsxq.com β
.content(Knowledge Planet)cnblogs.com β
.post(Blog Garden)Add more in
mcp-server/domain-rules.json(domain-selectors.jsonremains supported for compatibility)
Debug Tools
# 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:6274Data Directory (Optional)
By default, runtime data is stored under ~/Downloads/mcp-fetch-page/:
Cookies:
~/Downloads/mcp-fetch-page/cookiesPages:
~/Downloads/mcp-fetch-page/pages
For MCP usage, configure MCP_FETCH_PAGE_DATA_DIR in your MCP client config env field.
The server will always use:
<MCP_FETCH_PAGE_DATA_DIR>/cookies<MCP_FETCH_PAGE_DATA_DIR>/pages<MCP_FETCH_PAGE_DATA_DIR>/domain-rules.json(optional user overrides merged with built-in rules)
node mcp-server/server.js is only for local development/debugging.
Parameters
url(required): The URL to fetchwaitFor(optional): CSS selector to extract specific contentheadless(optional): Run browser in headless mode (default: true)timeout(optional): Timeout in milliseconds (default: 30000)
File Structure
mcp-fetch-page/
βββ package.json # npm package config
βββ package-lock.json # npm lockfile
βββ node_modules/ # npm dependencies
βββ README.md # This file
βββ README-zh.md # Chinese version
βββ CLAUDE.md # Claude Code usage guide
βββ chrome-extension/ # Chrome extension
β βββ manifest.json
β βββ popup.js
β βββ popup.html
β βββ background.js
βββ mcp-server/ # MCP server
βββ server.js # Main server
βββ debug.js # Debug tools
βββ domain-rules.json # Domain rules config (selector + blocked markers)
βββ domain-selectors.json # Legacy selector config (compatibility fallback)Troubleshooting
Extension not working: Make sure you're on a normal website (not chrome:// pages)
No cookies found: Try logging in again and saving cookies
MCP not connecting: Check Node.js installation and restart your editor
Path error: Set
MCP_FETCH_PAGE_DATA_DIRin MCP configenvto a writable absolute path on your machine/VPSCSS selector not working: Verify the selector exists on the page
That's it! πͺ
Available Tools
1 toolfetchpageA
Fetch web pages using browser automation with full JavaScript rendering. Supports automatic cookie management, localStorage, CSS selectors, and dynamic content. Cookies are automatically loaded from local storage if available.
Inputs: url (required), timeout, waitFor, headless.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 1 tool
With only one tool, there is no ambiguity. The tool has a clear and distinct purpose.
Single tool 'fetchpage' follows a clear verb_noun pattern (fetch + page), consistent with itself.
One tool is borderline for a server; it serves a focused purpose but lacks any auxiliary tools, making it thin.
The tool covers the core functionality of fetching pages with JS rendering and cookie management; minor gaps like explicit session listing exist but are not critical.
Maintenance
Related MCP Connectors
Web data extraction and browser workflows for AI assistants.
Fetch, crawl, and browse protected pages with anti-bot handling - renders in a real browser and
Read, crawl and act on websites, signed in as the user, and turn any site into an API.
AI-powered browser automation β navigate, click, fill forms, and extract data from any website.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceFetches content from authenticated web pages by driving your signed-in Chrome/Edge browser via DevTools Protocol, automatically handling login redirects and reusing sessions across domains.9MIT
- AlicenseNot gradedqualityCmaintenanceEnables LLMs to fetch and extract web content using browser automation, OCR, and multiple extraction methods, handling JavaScript rendering and anti-scraping techniques.17MIT
- AlicenseNot gradedqualityDmaintenanceFetches web pages with JavaScript rendering, pierces Shadow DOM, and enables interactive actions like clicking and form filling using a real Chrome browser.2MIT
- AlicenseNot gradedqualityBmaintenanceEnables headless-Chromium web automation, including rendering fully-executed HTML, extracting structured data with CSS selectors, capturing screenshots, and AI-assisted smart scraping of web pages.88 npmMIT