Deepseek Thinker MCP Server

What is Deepseek Thinker MCP Server about?

Deepseek Thinker MCP Server delivers the reasoning process (CoT) generated by the Deepseek model to any MCP‑compatible AI client such as Claude Desktop. It acts as a bridge that queries either the official Deepseek API or a locally hosted Ollama instance and returns structured reasoning output.

How to use Deepseek Thinker MCP Server?

1. Install – the server is distributed as an npm package. Use the convenient npx command to run it without a global install.
2. Configure – set environment variables for the chosen mode:
   • OpenAI API mode: API_KEY (your Deepseek/OpenAI key) and BASE_URL (API endpoint).
   • Ollama mode: USE_OLLAMA=true.
3. Integrate – add the server definition to the mcpServers section of the client configuration (e.g., claude_desktop_config.json).
4. Run – execute the npx command; the server will listen for MCP requests and return reasoning results.

Key Features of Deepseek Thinker MCP Server

• Dual Mode Support – works with the remote Deepseek OpenAI‑compatible API and with a local Ollama server.
• Structured Reasoning Output – captures and returns the model’s chain‑of‑thought process.
• TypeScript Implementation – includes strong type safety via Zod validation.
• Simple Integration – ready‑to‑use configuration snippets for Claude Desktop and other MCP clients.

Use Cases of Deepseek Thinker MCP Server

• Enhancing AI assistants with transparent reasoning steps.
• Debugging or auditing model decisions by exposing internal CoT.
• Building educational tools that illustrate how large language models think.
• Enabling offline reasoning with Ollama for privacy‑sensitive environments.

FAQ from the Deepseek Thinker MCP Server

• Why do I see “MCP error -32001: Request timed out”? The Deepseek API response took longer than the server’s timeout or the generated reasoning text exceeded the allowed length.
• Can I run the server locally without an internet connection? Yes, by setting USE_OLLAMA=true and having a local Ollama instance with the Deepseek model installed.
• What environment variables are required? For API mode: API_KEY and BASE_URL. For Ollama mode: USE_OLLAMA=true.
• Do I need to build the project before running? If you install via npm, the package is pre‑built. For source development, run npm install, npm run build, then node build/index.js.

Deepseek Thinker MCP Server

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.

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

Ollama Mode

Set the following environment variable:

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": "<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>"
      }
    }
  }
}

Development Setup

# Install dependencies
npm install

# Build project
npm run build

# 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)

License

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