66julienmartin MCP Server Deepseek R1

🚀 Deepseek R1 MCP Server

This is an implementation of the Model Context Protocol (MCP) server for the Deepseek R1 language model. Deepseek R1 is a powerful language model designed for inference tasks, with a context window size of 8192 tokens.

Why Node.js?

This implementation uses Node.js/TypeScript because it provides the most stable integration with the MCP server. The Node.js SDK offers better type safety, error handling, and compatibility with Claude Desktop.

🚀 Quick Start

Installation via Smithery

Automatically install Deepseek R1 for Claude Desktop using Smithery:

npx -y @smithery/cli install @66julienmartin/mcp-server-deepseek_r1 --client claude

Manual Installation

# Clone the code and install dependencies
git clone https://github.com/66julienmartin/MCP-server-Deepseek_R1.git
cd deepseek-r1-mcp
npm install

# Set up the environment
cp .env.example .env  # Then add your API key

# Build and run
npm run build

📋 Prerequisites

• Node.js (v18 or higher)
• npm
• Claude Desktop
• Deepseek API Key

🎯 Model Selection

By default, this server uses the deepseek-R1 model. If you wish to use the DeepSeek-V3 model, modify the model name in src/index.ts:

// Use Deepseek-R1 (default)
model: "deepseek-reasoner"

// Use Deepseek-V3
model: "deepseek-chat"

📁 Project Structure

deepseek-r1-mcp/
├── src/
│   ├── index.ts             # Main server implementation file
├── build/                   # Compiled files
│   ├── index.js
├── LICENSE
├── README.md
├── package.json
├── package-lock.json
└── tsconfig.json

⚙️ Configuration

1. Create a .env file:

DEEPSEEK_API_KEY=your-api-key-here

2. Update the Claude Desktop configuration:

{
  "mcpServers": {
    "deepseek_r1": {
      "command": "node",
      "args": ["/path/to/deepseek-r1-mcp/build/index.js"],
      "env": {
        "DEEPSEEK_API_KEY": "your-api-key"
      }
    }
  }
}

💻 Development

npm run dev     # Watch mode
npm run build   # Build for production

✨ Features

• Advanced text generation using Deepseek R1 (context window size of 8192)
• Configurable parameters (max_tokens, temperature)
• Robust error handling and detailed error messages
• Full MCP protocol support
• Claude Desktop integration
• Support for both DeepSeek-R1 and Deepseek-V3 models

📄 API Usage

{
  "name": "deepseek_r1",
  "arguments": {
    "prompt": "Your prompt here",
    "max_tokens": 8192,  // Maximum number of generated tokens
    "temperature": 0.7   // Creativity parameter, ranging from 0 to 1
  }
}

🌡️ Best Practices for Temperature Parameter

⚠️ Error Handling

• Input validation errors: Return 400 Bad Request
• Internal server errors: Return 500 Internal Server Error

🤝 Contribution

Contributions are welcome! Please refer to CONTRIBUTING.md.

📄 License

MIT License