RedNote (Xiaohongshu) MCP server

RedNote MCP is a service that allows you to access and interact with content from Xiaohongshu (Little Red Book), a popular Chinese social media platform. It implements the Model Context Protocol (MCP) to provide structured access to notes and search functionality.

Installation

Before installing, ensure you have the Playwright environment set up:

npx playwright install

Installing via NPM

The simplest way to install RedNote MCP is through NPM:

# Global installation
npm install -g rednote-mcp

# Initialize login (automatically saves cookies to ~/.mcp/rednote/cookies.json)
rednote-mcp init

Installing via Smithery

You can also install RedNote MCP for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @JonaFly/rednote-mcp --client claude

Installing from Source

# Clone the repository
git clone https://github.com/ifuryst/rednote-mcp.git
cd rednote-mcp

# Install dependencies
npm install

# Optional: Install globally for command-line usage
npm install -g .

# Or run directly, e.g., for initialization
npm run dev -- init

Usage Guide

Initial Login

Before using RedNote MCP, you must initialize it with a login:

rednote-mcp init
# Or run directly from source
npm run dev -- init
# Or select login from mcp-client

When you run this command:

1. A browser window will open automatically
2. You'll be redirected to the Xiaohongshu login page
3. Complete the login process manually
4. After successful login, cookies will be saved to ~/.mcp/rednote/cookies.json

Configuring with Cursor

To use RedNote MCP with Cursor, add the following configuration to your Cursor's settings.json:

{
  "mcpServers": {
    "RedNote MCP": {
      "command": "rednote-mcp",
      "args": [
        "--stdio"
      ]
    }
  }
}

Alternatively, you can use the npx approach:

{
  "mcpServers": {
    "RedNote MCP": {
      "command": "npx",
      "args": [
        "rednote-mcp",
        "--stdio"
      ]
    }
  }
}

Configuration details:

• command: Can be the globally installed rednote-mcp command or npx to run directly
• args: Must include --stdio parameter to support Cursor's communication method

Debugging with MCP Inspector

For debugging the MCP server, you can use the MCP Inspector tool:

npx @modelcontextprotocol/inspector npx rednote-mcp --stdio

This command:

1. Launches the MCP Inspector tool
2. Runs the rednote-mcp service through the Inspector
3. Provides an interactive interface to examine requests and responses
4. Helps with debugging and validating the MCP protocol implementation

Important Notes

• You must run the init command for initial login before using other features
• The cookies file contains sensitive information - keep it secure
• Update your cookies periodically to prevent expiration
• Ensure you have a proper Node.js environment installed

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.