Deepseek Thinker MCP Server

Core Features

• 🤖 Dual Mode Support
• OpenAI API mode support
• Ollama local mode support
• 🎯 Focused Reasoning
• Captures Deepseek's thinking process
• Provides reasoning output

Available Tools# get-deepseek-thinker

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

Environment Configuration# OpenAI API Mode

Set the following environment variables:

API_KEY=
BASE_URL=
```\n\n### Ollama Mode
Set the following environment variable:
```bash
USE_OLLAMA=true

Usage# Integration with AI Client, like Claude Desktop

Add the following configuration to your claude_desktop_config.json:

{
  "mcpServers": {
    "deepseek-thinker": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-thinker-mcp"
      ],
      "env": {
        "API_KEY": "",
        "BASE_URL": ""
      }
    }
  }
}
```\n\n### Using Ollama Mode
```json
{
  "mcpServers": {
    "deepseek-thinker": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-thinker-mcp"
      ],
      "env": {
        "USE_OLLAMA": "true"
      }
    }
  }
}
```\n\n### Local Server Configuration
```json
{
  "mcpServers": {
    "deepseek-thinker": {
      "command": "node",
      "args": [
        "/your-path/deepseek-thinker-mcp/build/index.js"
      ],
      "env": {
        "API_KEY": "",
        "BASE_URL": ""
      }
    }
  }
}

Development Setup

npm install\n\n# Build project
npm run build\n\n# Run service
node build/index.js

FAQ# Response like this: "MCP error -32001: Request timed out"

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.

Tech Stack

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