Deepseek R1 MCP Server

Deepseek R1 MCP Server provides seamless integration between Claude Desktop and DeepSeek's powerful language models. This implementation supports both DeepSeek-R1, optimized for reasoning tasks with an 8192 token context window, and DeepSeek-V3, offering users flexibility in model selection based on their specific needs. Built with Node.js/TypeScript for optimal stability, type safety, and error handling, this MCP server ensures reliable communication between Claude Desktop and DeepSeek's API. Users can configure various parameters including temperature settings tailored for different use cases from coding and data analysis to creative writing.

Installation

Prerequisites

Node.js (v18 or higher)
npm
Claude Desktop
DeepSeek API key

Manual Installation

Clone the repository and install dependencies:

git clone https://github.com/66julienmartin/MCP-server-Deepseek_R1.git
cd MCP-server-Deepseek_R1
npm install

Create a .env file in the project root:

DEEPSEEK_API_KEY=your-api-key-here

Build the project:

npm run build

Configure Claude Desktop by adding the following to your configuration:

{
  "mcpServers": {
    "deepseek_r1": {
      "command": "node",
      "args": ["/path/to/MCP-server-Deepseek_R1/build/index.js"],
      "env": {
        "DEEPSEEK_API_KEY": "your-api-key"
      }
    }
  }
}

Usage

Once installed, you can use the Deepseek R1 model through Claude Desktop. The server supports the following parameters:

prompt: Your input text
max_tokens: Maximum tokens to generate (up to 8192)
temperature: Controls randomness of the output

Model Selection

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

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

// For DeepSeek-V3
model: "deepseek-chat"

Temperature Settings

The default temperature value is 0.2. DeepSeek recommends different temperature settings based on your use case:

| Use Case | Temperature | Example | |----------|-------------|---------| | Coding / Math | 0.0 | Code generation, mathematical calculations | | Data Cleaning / Analysis | 1.0 | Data processing tasks | | General Conversation | 1.3 | Chat and dialogue | | Translation | 1.3 | Language translation | | Creative Writing / Poetry | 1.5 | Story writing, poetry generation |

Development

For development purposes, you can run the server in watch mode:

npm run dev

Troubleshooting

The server provides detailed error messages for common issues:

API authentication errors: Check that your DeepSeek API key is correct
Invalid parameters: Ensure your parameters are within acceptable ranges
Rate limiting: You may need to wait before making additional requests
Network issues: Check your internet connection

If you encounter persistent issues, check the server logs for more detailed error information.