Description

Reads and extracts content from WeChat official account articles using Playwright for browser automation and BeautifulSoup for HTML parsing. Simulates browser behavior to bypass anti-scraping measures and returns structured article data including title, author, publication date, and full content. Designed for content aggregation, research workflows involving Chinese social media, and automated monitoring of WeChat public accounts.

Installation

git clone https://github.com/bwkyd/wexin-read-mcp

Claude Desktop Configuration

Add this configuration to your Claude Desktop config file to enable this MCP server:

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json

Config file location: %APPDATA%\Claude\claude_desktop_config.json

Config file location: ~/.config/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "wechat-articles": {
      "command": "node",
      "args": [
        "path/to/server.js"
      ]
    }
  }
}