Deepseek Thinker MCP

🚀 DeepSeek Thinker MCP Server

A Model Context Protocol (MCP) provider for DeepSeek inference content, enabling the transfer of content to MCP - enabled AI clients like Claude Desktop via the DeepSeek API service or a local Ollama server. It allows access to the DeepSeek inference process.

🚀 Quick Start

This is a MCP provider for DeepSeek inference content. It supports two modes to transfer content to MCP - enabled AI clients, and can access the DeepSeek inference process.

✨ Features

• 🤖 Dual - Mode Support

  • Support for OpenAI API mode
  • Support for local Ollama mode

• 🎯 Focus on Inference

  • Capture the DeepSeek thinking process
  • Provide inference output

📦 Available Tools

get - deepseek - thinker

• Description: Perform inference using the DeepSeek model.
• Input Parameters:
  • originPrompt (string): The user's original prompt.
• Return: A structured text response containing the thinking process.

📦 Installation

OpenAI API Mode

Set the following environment variables:

API_KEY=<Your OpenAI API Key>
BASE_URL=<API Base URL>

Ollama Mode

Set the following environment variable:

USE_OLLAMA=true

💻 Usage Examples

Integration with AI Clients (e.g., Claude Desktop)

Add the following configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "deepseek - thinker": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek - thinker - mcp"
      ],
      "env": {
        "API_KEY": "<Your API Key>",
        "BASE_URL": "<Your Base URL>"
      }
    }
  }
}

Using Ollama Mode

{
  "mcpServers": {
    "deepseek - thinker": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek - thinker - mcp"
      ],
      "env": {
        "USE_OLLAMA": "true"
      }
    }
  }
}

Local Server Configuration

{
  "mcpServers": {
    "deepseek - thinker": {
      "command": "node",
      "args": [
        "/your - path/deepseek - thinker - mcp/build/index.js"
      ],
      "env": {
        "API_KEY": "<Your API Key>",
        "BASE_URL": "<Your Base URL>"
      }
    }
  }
}

📚 Documentation

Development Setup

# Install dependencies
npm install

# Build the project
npm run build

# Run the service
node build/index.js

Frequently Asked Questions

How to solve a response like "MCP Error - 32001: Request Timeout"?

This error occurs when the DeepSeek API response is too slow or the inference content output is too long, causing the MCP server to time out.

🔧 Technical Details

📄 License

This project is released under the MIT License. See the LICENSE file for details.