MCP-Mirror

DeepSeek MCP Server

Community MCP-Mirror
Updated

Model Context Protocol server for DeepSeek's advanced language models.

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

  1. Get your DeepSeek API key from DeepSeek Platform

  2. 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:

  1. Build the server:

    npm run build
    
  2. 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

MCP Server · Populars

MCP Server · New

    render-oss

    Render MCP Server

    The Official Render MCP Server

    Community render-oss
    nhevers

    claude-recall

    Long-term memory layer for Clawd & Claude Code that learns and recalls your project context automatically

    Community nhevers
    VienLi

    lark-tools-mcp

    MCP server provides Feishu related operations to AI encoding agents such as cursor 飞书MCP插件,读取文档、发送消息、合同审批、数据处理.....

    Community VienLi
    joeseesun

    🎯 多源内容 → NotebookLM 智能处理器

    Claude Skill: Multi-source content processor for NotebookLM. Supports WeChat articles, web pages, YouTube, PDF, Markdown, search queries → Podcast/PPT/MindMap/Quiz etc.

    Community joeseesun
    avivsinai

    Langfuse MCP Server

    A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

    Community avivsinai