MCP Server Deepseek R1

🚀 Deepseek R1 MCP Server

Deepseek R1 is a powerful language model designed for inference tasks, featuring a context window of 8192 tokens. This implementation uses Node.js/TypeScript as 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

Manual Installation

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

# Environment configuration
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 want to use the DeepSeek-V3 instead, modify the model name in src/index.ts:

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

// For 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

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 (8192 token context window)
• Configurable parameters (max_tokens, temperature)
• Robust error handling with detailed error messages
• Full support for the MCP protocol
• Claude Desktop integration
• Support for DeepSeek-R1 and DeepSeek-V3 models

💻 Usage Examples

Basic Usage

{
  "name": "deepseek_r1",
  "arguments": {
    "prompt": "Your prompt statement",
    "max_tokens": 8192,    // Maximum number of generated tokens
    "temperature": 0.2     // Temperature parameter
  }
}

Temperature Parameter Explanation

✨ Error Handling

⚠️ Important Note

• Error: Invalid API key

• Check if the DEEPSEEK_API_KEY in the .env file is correct.

• Error: Unable to connect to the server

  • Ensure that the server is started and running.

• Error: Model not loaded

  • Check if the model name in src/index.ts is configured correctly.

💻 Usage Examples

Basic Usage

npm install
node src/index.js

Input prompt statement:

"Tell me some tips for creative writing."

Output result:

{
  "response": "1. Use vivid language and specific details to depict scenes.\n2. Read excellent works to gain inspiration.\n3. Practice daily writing to improve skills."
}

✨ Summary

By following the above steps, you can easily configure and run the Deepseek R1 MCP server, leveraging its powerful language model for various text generation tasks.