Deepseek R1 MCP Server

Deepseek R1 MCP Server

What is Deepseek R1 MCP Server?

The Deepseek R1 MCP Server is a Node.js/TypeScript implementation of a Model Context Protocol (MCP) server. It facilitates the connection between Claude Desktop and DeepSeek's powerful language models, specifically R1 and V3. Deepseek R1 is highlighted for its reasoning capabilities and an 8192 token context window. The choice of Node.js is attributed to its stability, type safety, error handling, and compatibility with Claude Desktop for MCP servers.

How to use Deepseek R1 MCP Server?

1. Clone the repository:

   git clone https://github.com/66julienmartin/MCP-server-Deepseek_R1.git
   cd deepseek-r1-mcp
   

2. Install dependencies:

   npm install
   

3. Set up environment variables: Copy .env.example to .env and add your Deepseek API key.

   cp .env.example .env
   # Add DEEPSEEK_API_KEY=your-api-key-here to the .env file
   

4. Build the project:

   npm run build
   

5. Configure Claude Desktop: Update your Claude Desktop configuration with the path to the built server file and your API key.

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

6. Model Selection: By default, the server uses deepseek-R1. To use DeepSeek-V3, change the model value in src/index.ts from "deepseek-reasoner" to "deepseek-chat".

Key Features of Deepseek R1 MCP Server

• Advanced Text Generation: Utilizes Deepseek R1 with an 8192 token context window.
• Model Compatibility: Supports both DeepSeek-R1 and DeepSeek-V3 models.
• Claude Desktop Integration: Seamlessly connects with Claude Desktop via the MCP protocol.
• Configurable Parameters: Allows adjustment of max_tokens and temperature.
• Robust Error Handling: Provides detailed error messages for common issues like API authentication, invalid parameters, rate limiting, and network problems.
• Development Tools: Includes scripts for development (watch mode) and production builds.

Use Cases of Deepseek R1 MCP Server

• Coding and Math: Optimized for tasks requiring precision and logical steps with a low temperature setting (0.0).
• Data Cleaning and Analysis: Suitable for data processing tasks with a temperature of 1.0.
• General Conversation and Creative Writing: Can be used for dialogue, story writing, and poetry generation with higher temperature settings (1.3-1.5).
• Translation: Supports language translation tasks.

FAQ about Deepseek R1 MCP Server

• What are the prerequisites? Node.js (v18 or higher), npm, Claude Desktop, and a Deepseek API key.
• How to switch between DeepSeek-R1 and DeepSeek-V3? Modify the model name in src/index.ts. Use "deepseek-reasoner" for R1 and "deepseek-chat" for V3.
• How is the temperature parameter used? The temperature parameter controls the randomness of the output. Lower values (e.g., 0.0) are for deterministic tasks like coding, while higher values (e.g., 1.5) are for creative tasks. The project provides a table suggesting temperature values for different use cases.
• How to contribute? Contributions are welcome via Pull Requests.

The project is licensed under the MIT license.

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