WeRead MCP server

This lightweight server bridges WeChat Reading (微信读书) data with Claude Desktop, allowing you to seamlessly access your reading notes and data within Claude through the Model Context Protocol (MCP).

Installation

Prerequisites

• Node.js (v16+) installed on your system
• WeChat Reading account and cookies

Setup Steps

1. Clone the repository:

   git clone https://github.com/yourusername/mcp-server-weread.git
   

2. Navigate to the project directory:

   cd mcp-server-weread
   

3. Install dependencies:

   npm install
   

   If downloads are slow, you can use:

   npm install --registry=https://registry.npmmirror.com
   

Obtaining WeChat Reading Cookies

1. Log in to WeChat Reading web version: https://weread.qq.com/
2. Open browser developer tools (F12 or right-click Inspect)
3. Switch to the "Application" tab
4. Find "Cookies" under "Storage" in the left panel
5. Select "https://weread.qq.com"
6. Find and copy all cookie values (select all and copy)

Configuration

1. Edit the .env file in the project root directory
2. Set the WeChat Reading cookie:

   WEREAD_COOKIE=your_copied_cookie_value
   

Starting the Server

1. Build the code:

   npm run build
   

2. Start the server:

   node build/index.js
   

MCP Client Configuration

For Cursor AI, add the following to your ~/.cursor/mcp.json file:

{
  "mcpServers": {
    "mcp-server-weread": {
      "command": "node",
      "args": ["/path/to/mcp-server-weread/build/index.js"],
      "env": {
        "WEREAD_COOKIE": "your_weread_cookie"
      }
    }
  }
}

Replace /path/to/mcp-server-weread with the actual installation path and set the correct cookie value.

Available Tools

The server provides several tools to access your WeChat Reading data:

• get_bookshelf - Retrieves your complete bookshelf information
• get_notebooks - Gets a list of books containing your notes
• get_book_notes - Retrieves all notes for a specific book
• get_book_info - Gets detailed information about a book
• search_notes - Searches all notes for specific keywords
• get_recent_reads - Retrieves your recently read books and related data

Usage Examples

In an MCP-compatible AI client (like Claude Desktop), you can make requests like:

• "Show me the books on my bookshelf"
• "I'd like to see my notes from 'Thinking, Fast and Slow'"
• "Help me find notes about 'cognitive bias'"
• "Get my recently read books"

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.