deepseek-thinker-mcp

A MCP (Model Context Protocol) provider Deepseek reasoning content to MCP-enabled AI Clients, like Claude Desktop. Supports access to Deepseek's thought processes from the Deepseek API service or from a local Ollama server.

• 🤖 Dual Mode Support

  • OpenAI API mode support
  • Ollama local mode support

• 🎯 Focused Reasoning

  • Captures Deepseek's thinking process
  • Provides reasoning output

• Description: Perform reasoning using the Deepseek model
• Input Parameters:
  • originPrompt (string): User's original prompt
• Returns: Structured text response containing the reasoning process

Set the following environment variables:

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

Set the following environment variable:

USE_OLLAMA=true

Add the following configuration to your claude_desktop_config.json:

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

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

{
  "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>"
      }
    }
  }
}

# Install dependencies
npm install

# Build project
npm run build

# Run service
node build/index.js

This error occurs when the Deepseek API response is too slow or when the reasoning content output is too long, causing the MCP server to timeout.

• TypeScript
• @modelcontextprotocol/sdk
• OpenAI API
• Ollama
• Zod (parameter validation)

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