🌟 Overview

Pulse CN MCP Server enables AI models to access up-to-date information about what’s trending on the Chinese internet. Built with the Model Context Protocol (MCP), it acts as a bridge between AI models and real-time data from China’s most popular social media platforms, news sites, and content aggregators.

✨ Features

The server provides real-time access to trending data from 18 major Chinese platforms:

🚀 Installation

# Clone the repository
git clone https://github.com/wangtsiao/pulse-cn-mcp.git

# Navigate to the project directory
cd pulse-cn-mcp

# Using npm
npm install
npm run build

# Or using Bun (faster)
bun install
bun run build

⚡ Quick Start

Start the MCP server with:

# Using npm
npm start

# Or using Bun
bun start

This launches the server using the Stdio transport, making it ready for MCP-compatible AI models to connect.

📖 Documentation

Architecture

Pulse CN MCP Server follows a modular architecture with individual tools for each data source:

src/
├── index.ts            # Main entry point and server setup
└── tools/              # Individual tool implementations
    ├── weiboHotspots.js
    ├── horoscope.js
    ├── dailyEnglishSentence.js
    ├── internetHotspotsAggregator.js
    ├── todayHeadlinesHotspots.js
    ├── paperNewsHotspots.js
    └── otherHotspots.js

Available Tools

Fully Implemented

Coming Soon

• hupu-pedestrian-street-hotspots
• zhihu-realtime-hotspots
• zhihu-daily-hotspots
• 36-krypton-24-hour-hotspots
• bilibili-daily-hotspots
• baidu-hotspots
• douyin-hotspots
• douban-group-hotspots
• huxiu-hotspots
• product-manager-hotspots
• in-information-hotspots
• insect-hotspots

Integration Example

Here’s how to integrate with the server using TypeScript:

import { McpClient } from "@modelcontextprotocol/sdk/client";

async function example() {
  const client = new McpClient();
  
  // Get Weibo trending topics
  const weiboHotspots = await client.callTool("weibo-hotspots", {});
  console.log(weiboHotspots.content);
  
  // Get daily horoscope for Aries
  const horoscope = await client.callTool("horoscope", { sign: "aries" });
  console.log(horoscope.content);
}

🛠️ Development

Adding a New Tool

1. Create a new file in src/tools/ (e.g., myNewTool.ts)
2. Implement your tool using the MCP Server SDK
3. Register the tool in src/index.ts

Example:

// src/tools/myNewTool.ts
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { z } from "zod";

export function registerMyNewTool(server: McpServer) {
  server.tool(
    "my-new-tool",
    "Description of my new tool",
    {
      // Tool parameters schema
      param1: z.string().describe("Parameter description")
    },
    async (params) => {
      // Tool implementation
      return {
        content: [
          { type: "text", text: "Result of my tool" }
        ]
      };
    }
  );
}

// src/index.ts - Add import and registration
import { registerMyNewTool } from './tools/myNewTool.js';
// ...
registerMyNewTool(server);

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the project
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

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

🙏 Acknowledgements

This project utilizes the free APIs provided by 韩小韩API. We express our sincere gratitude for their excellent service and support.