DeepSeek MCP Server

A Model Context Protocol (MCP) server for the DeepSeek API, allowing seamless integration of DeepSeek's powerful language models with MCP-compatible applications like Claude Desktop.

Installation

npm install -g deepseek-mcp-server

Configuration

Get your DeepSeek API key from DeepSeek Platform

Set up your environment:

export DEEPSEEK_API_KEY=your-api-key

Or create a .env file:

DEEPSEEK_API_KEY=your-api-key

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

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

Features

Chat completion tool with support for:
- Custom model selection
- Temperature control
- Max tokens limit
- Top P sampling
- Presence penalty
- Frequency penalty

Testing with MCP Inspector

You can test the server locally using the MCP Inspector tool:

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

Run the server with MCP Inspector:

# Make sure to specify the full path to the built server
npx @modelcontextprotocol/inspector node ./build/index.js

The inspector will open in your browser and connect to the server via stdio transport. You can:

View available tools
Test chat completions with different parameters
Debug server responses
Monitor server performance

Note: The server uses DeepSeek's R1 model (deepseek-reasoner) by default, which provides state-of-the-art performance for reasoning and general tasks.

License

MIT

Fidelis Memory

Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusion retrieval. Returns original passages verbatim by default. Available on PyPI as fidelis-memory. MIT.

DeepSeek MCP Server