MCP Server Qwen Max

🚀 Qwen Max MCP Server Implementation

This project aims to support Qwen series models (including Qwen-Max, Qwen-Plus, and Qwen-Turbo), providing text generation services through the MCP protocol. It is developed using Node.js and TypeScript, offering higher stability and reliability compared to Python.

🚀 Quick Start

📦 Installation

Automatic Installation

Use the Smithery CLI tool for automatic installation:

smith install Qwen_Max

Manual Installation

1. Clone the project repository:

   git clone https://github.com/your-username/Qwen_Max.git
   cd Qwen_Max
   

2. Install dependencies:

   npm install
   

📁 Project Structure

Qwen_Max/
├── src/              # Source code directory, including the main program entry index.ts, etc.
├── build/            # Compiled production files
├── .env              # Environment variable configuration file
├── README.md         # Project documentation
├── package.json      # Dependency management and running scripts
└── tsconfig.json     # TypeScript configuration file

⚙️ Configuration

1. Create a .env file and add the following content:

   DASHSCOPE_API_KEY=your-api-key-here
   

2. Update the configuration file claudius.json of Claude Desktop:

   {
     "mcpServers": {
       "qwen_max": {
         "command": "node",
         "args": ["/path/to/Qwen_Max/build/index.js"],
         "env": {
           "DASHSCOPE_API_KEY": "your-api-key-here"
         }
       }
     }
   }
   

💻 Development

npm run dev     # Start development mode with automatic compilation support
npm run build   # Build the production version
npm run start   # Start the server

✨ Features

• Text Generation: Supports text generation based on Qwen models.
• Configurable Parameters: Allows setting parameters such as max_tokens and temperature.
• Error Handling: Provides detailed error information for easy troubleshooting.
• MCP Protocol Support: Compatible with the MCP protocol, enabling seamless integration with other tools and services.
• Claude Desktop Integration: Deeply integrated with the Claude Desktop tool.

💻 Usage Examples

Basic Usage

// Example tool call
{
  "name": "qwen_max",
  "arguments": {
    "prompt": "Your prompt here",
    "max_tokens": 8192,
    "temperature": 0.7
  }
}

🌡️ Temperature Parameter Explanation

• Range: 0.0 to 1.0.
• Impact:
  • Lower values (0.0 - 0.7): Output is more focused and deterministic.
  • Higher values (0.7 - 1.0): Output is more creative and diverse.

Recommended Use Cases

• Code Generation: Set the temperature to 0.0 - 0.3 to ensure output accuracy and reliability.
• Technical Writing: Set the temperature to 0.3 - 0.5 to balance accuracy and some creativity.
• General Tasks: Default temperature of 0.7, suitable for most scenarios.
• Creative Writing: Set the temperature to 0.8 - 1.0 to inspire creativity.

❌ Error Handling

The server provides detailed error information for common issues:

• API authentication failure
• Invalid parameters
• Request rate limit
• Network connection issues
• Account usage restrictions
• Model service exceptions

🤝 Project Contribution

Welcome community developers to actively participate in the improvement and optimization of the project by submitting Pull Requests to contribute code.

📄 License

This project is licensed under the MIT License, allowing users to freely use, modify, and distribute the project code.