Deepseek R1 MCP Server

Deepseek R1 MCP Server

What is Deepseek R1 MCP Server about?

The project implements a Model Context Protocol (MCP) server using Node.js/TypeScript. It bridges Claude Desktop with DeepSeek's powerful language models (R1 and V3), exposing the models through a stable, type‑safe interface that supports full MCP protocol features.

How to use Deepseek R1 MCP Server?

1. Install

   git clone https://github.com/66julienmartin/MCP-server-Deepseek_R1.git
   cd deepseek-r1-mcp
   npm install
   cp .env.example .env   # add your DeepSeek API key
   npm run build
   

2. Run (production)

   node build/index.js
   

   or in development mode:

   npm run dev   # watches source files
   

3. Configure Claude Desktop by adding a server entry similar to:

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

4. Switch to DeepSeek‑V3 – edit src/index.ts and change the model name from deepseek-reasoner to deepseek-chat.

Key features of Deepseek R1 MCP Server

• Supports DeepSeek‑R1 (8192 token context) and DeepSeek‑V3 models.
• Full MCP protocol compliance for seamless Claude Desktop integration.
• Configurable generation parameters: max_tokens, temperature, etc.
• Robust error handling with clear messages for authentication, rate‑limits, and network issues.
• Type‑safe TypeScript codebase, easy to extend.
• Simple environment‑based configuration (DEEPSEEK_API_KEY).

Use cases of Deepseek R1 MCP Server

• Coding & math assistance – low temperature (0.0) for deterministic outputs.
• Data cleaning / analysis – higher temperature (1.0) to explore varied transformations.
• General conversation or chatbots – temperature around 1.3 for natural dialogue.
• Translation – temperature 1.3 for fluent multilingual output.
• Creative writing & poetry – temperature 1.5 to encourage imaginative text.

FAQ

• How do I change the model to DeepSeek‑V3? Edit src/index.ts and replace model: "deepseek-reasoner" with model: "deepseek-chat".
• What is the maximum token limit? DeepSeek‑R1 supports up to 8192 tokens per request; you can set max_tokens accordingly.
• Where do I store my API key? Add DEEPSEEK_API_KEY=your-key to the .env file; the server reads it at runtime.
• Can I run the server without building? Yes, use npm run dev for on‑the‑fly TypeScript compilation in watch mode.
• What happens if I exceed the rate limit? The server returns a detailed error message indicating the limit and suggests retrying after the specified back‑off period.

Deepseek R1 MCP Server

A Model Context Protocol (MCP) server implementation for the Deepseek R1 language model. Deepseek R1 is a powerful language model optimized for reasoning tasks with a context window of 8192 tokens.

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

Quick Start

Installing manually

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

# Set up 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 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"

Project Structure

deepseek-r1-mcp/
├── src/
│   ├── index.ts             # Main server implementation
├── 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 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 with Deepseek R1 (8192 token context window)
• Configurable parameters (max_tokens, temperature)
• Robust error handling with 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 tokens to generate
    "temperature": 0.2     // Controls randomness
  }
}

The Temperature Parameter

The default value of temperature is 0.2.

Deepseek recommends setting the temperature according to your specific use case:

USE CASE	TEMPERATURE	EXAMPLE
Coding / Math	0.0	Code generation, mathematical calculations
Data Cleaning / Data 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

Error Handling

The server provides detailed error messages for common issues:

• API authentication errors
• Invalid parameters
• Rate limiting
• Network issues

Contributing

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

License

MIT