Rednote MCP

🚀 RedNote MCP - Xiaohongshu Content Search Tool

RedNote MCP is a Model Context Protocol (MCP) server designed for searching and retrieving content from the Xiaohongshu (Red Book) platform. It offers intelligent content extraction, featuring automatic login management and parallel processing capabilities, which greatly enhances the efficiency of content retrieval.

🚀 Quick Start

After ensuring that the prerequisites are met, you can quickly start using RedNote MCP by following the installation steps and running the MCP server.

✨ Features

• Smart Search: Conduct keyword-based content searches on Xiaohongshu.
• Auto Login: Automatically manage cookies and handle the login process.
• Parallel Processing: Efficiently retrieve content concurrently.
• Rich Data Extraction:
  • Extract note titles and content.
  • Gather author information and descriptions.
  • Collect interaction metrics such as likes, favorites, and comments.
  • Obtain images and hashtags.
  • Retrieve direct note links.

🔧 Technical Details

• Runtime: Node.js with TypeScript
• Browser Automation: Playwright
• Protocol: Model Context Protocol (MCP) SDK
• Validation: Zod schema validation
• Package Manager: pnpm

💻 Usage Examples

Basic Usage

The data structure of the retrieved content is as follows:

interface RedBookNote {
  title: string;        // Note title
  content: string;      // Note content
  author: string;       // Author name
  authorDesc?: string;  // Author description
  link: string;         // Note URL
  likes?: number;       // Like count
  collects?: number;    // Favorite count
  comments?: number;    // Comment count
  tags?: string[];      // Hashtag list
  images?: string[];    // Image URLs (WebP format)
}

Advanced Usage

Installation

Ensure you have Node.js 18+ and the pnpm package manager installed. Then follow these steps:

1. Clone the repository:

git clone <repository-url>
cd rednote-mcp

2. Install dependencies:

pnpm install

3. Install Playwright browsers:

pnpm exec playwright install

4. Build the project:

pnpm build

Running the MCP Server

pnpm start

Development Mode

pnpm dev

Testing

pnpm test

MCP Client Configuration

Claude Desktop

Add the following configuration to your Claude Desktop config file: Windows: %APPDATA%\Claude\claude_desktop_config.json macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "rednote-mcp": {
      "command": "node",
      "args": [
        "C:\\ABSOLUTE\\PATH\\TO\\rednote-mcp\\build\\index.js"
      ]
    }
  }
}

For macOS/Linux users:

{
  "mcpServers": {
    "rednote-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/rednote-mcp/build/index.js"
      ]
    }
  }
}

Replace the path with your actual project directory.

Other MCP Clients

For other MCP-compatible clients, use the built server file:

node build/index.js

Tool Usage

Once configured, you can use the search tool in your MCP client:

Search for "food recommendation" on Xiaohongshu

The tool will return structured data including titles, content, author information, and images.

📚 Documentation

Development

Project Structure

rednote-mcp/
├── src/
│   ├── index.ts          # MCP server entry point
│   └── xiaohongshu.ts    # Core scraping logic
├── cookies/              # Auto-generated cookie storage
├── results/              # Optional: saved search results
├── build/                # Compiled JavaScript output
├── package.json
├── tsconfig.json
└── README.md

Available Scripts

• pnpm build - Build TypeScript to JavaScript
• pnpm start - Run the built MCP server
• pnpm dev - Development mode with auto-reload
• pnpm test - Run tests (if available)
• pnpm clean - Clean build directory

Troubleshooting

Common Issues

1. Login Required: If you see login prompts, delete the cookies/ directory and restart.
2. Timeout Errors: Increase the MCP client timeout settings.
3. Browser Not Found: Run pnpm exec playwright install to install browsers.
4. Permission Errors: Ensure the project directory has proper read/write permissions.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

⚠️ Important Note

• On the first run, manual login to Xiaohongshu is required.
• Initial searches may take 30 - 60 seconds due to browser startup and content loading.
• Concurrent requests are limited to 3 to avoid platform restrictions.
• Images are provided in WebP format.
• Login state is automatically saved and reused.

💡 Usage Tip

This tool is for educational and research purposes. Please respect Xiaohongshu's terms of service and rate limits when using this tool.