📌Overview

Purpose: The DeepSeek MCP Server aims to facilitate seamless integration of DeepSeek's language models with applications supporting the Model Context Protocol (MCP), ensuring user anonymity through proxy usage.

Overview: The DeepSeek MCP Server acts as a bridge between DeepSeek's advanced language models and various MCP-compatible applications, such as Claude Desktop. It simplifies user interactions through natural language requests while maintaining robust performance and configuration management.

Key Features:

Automatic Model Fallback: If the primary model deepseek-reasoner is unavailable, the server automatically switches to a backup model, deepseek-chat, optimizing for speed and usage across different scenarios.
Multi-turn Conversation Support: This feature enables the server to maintain complete message history and context throughout conversational exchanges, crucial for complex discussions and training dialogue models.
Resource Discovery: Users can easily query available models, configuration settings, and customize options like temperature, token limits, and penalties to enhance their interaction experience.

DeepSeek MCP Server

A Model Context Protocol (MCP) server for the DeepSeek API, enabling integration of DeepSeek's language models with MCP-compatible applications.

Anonymous Usage

You can use the DeepSeek API anonymously; only a proxy is seen on the other side.

Installation

Install via Smithery

To automatically install DeepSeek MCP Server for Claude Desktop via Smithery:

npx -y @smithery/cli install @dmontgomery40/deepseek-mcp-server --client claude

Manual Installation

npm install -g deepseek-mcp-server

Usage with Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "deepseek": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-mcp-server"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "your-api-key"
      }
    }
  }
}

Features

Natural Language Requests: The server handles requests intelligently by mapping them to configuration changes. You can inquire about available models, configuration options, and current settings.
Automatic Model Fallback: If the primary model (R1) is down, the server automatically switches to the v3 model. Users can switch models anytime by specifying their prompt.
Resource Discovery: The server supports:
- Custom model selection
- Temperature control (0.0 - 2.0)
- Max tokens limit
- Top P sampling (0.0 - 1.0)
- Presence penalty (-2.0 - 2.0)
- Frequency penalty (-2.0 - 2.0)

Enhanced Conversation Features

Multi-turn Conversation Support: Maintains message history, context, and configuration settings, facilitating complex interactions such as training, technical discussions, and troubleshooting.

Testing with MCP Inspector

Test the server locally using the MCP Inspector tool:

Build the server:
```
npm run build
```

Run the server with MCP Inspector:

npx @modelcontextprotocol/inspector node ./build/index.js

The inspector connects to the server via stdio transport, allowing you to:

View available tools
Test chat completions
Debug server responses
Monitor performance

License

MIT