Deepseek R1 Reasoning

🚀 DeepSeek MCP Server

Enhance Claude's inference capabilities with the advanced inference engine of DeepSeek R1.

🚀 Quick Start

This server enhances Claude's ability to handle complex inference tasks by integrating the advanced inference engine of DeepSeek R1.

✨ Features

Enhanced Inference Capability for Claude

By integrating the advanced inference engine of DeepSeek R1, this server enables Claude to handle complex inference tasks, leveraging the inference power of the DeepSeek R1 model.

• DeepSeek R1 (Brain): Serves as an advanced inference planner.

  • Plans multi - step logical analysis strategies.
  • Builds cognitive frameworks.
  • Evaluates confidence and uncertainty.
  • Monitors inference quality.
  • Detects boundary cases and biases.

• Claude (Executor): Implements the inference plan.

  • Performs structured analysis.
  • Implements predetermined strategies.
  • Outputs the final response.
  • Handles user interactions.
  • Manages system integration.

Advanced Inference Ability

• Supports complex multi - step inference tasks.
• Designed to generate precise and efficient, well - thought - out responses.
• Uses the API of Infini - AI (Access URL).

📦 Installation

Prerequisites

• Python 3.12 or higher.
• uv package manager.
• INFINI_API_KEY from DeepSeek (Register at Infini - AI to obtain).

1. Clone the repository

   git clone https://github.com/moyu6027/deepseek-MCP-server.git
   cd deepseek-MCP-server
   

2. Ensure UV is installed

   • Windows: Run in PowerShell:

     powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
     

   • Mac: Run the following command:

     curl -LsSf https://astral.sh/uv/install.sh | sh
     

3. Create a virtual environment

   uv venv
   source .venv/bin/activate
   

4. Install dependencies

   uv add "mcp[cli]" httpx
   

5. Set the API key

   echo "INFINI_API_KEY=your_key_here" > .env
   

6. Install the server

   mcp install server.py -f .env
   

7. Configure the MCP server Edit the claude_desktop_config.json file and add the following configuration:

   {
       "mcpServers": {
           "deepseek-mcp": {
               "command": "uv",
               "args": [
                   "--directory",
                   "PATH_TO_DEEPSEEK_MCP_SERVER",
                   "run",
                   "server.py"
               ]
           }
       }
   }
   

8. Run the server

   uv run server.py
   

💻 Usage Examples

Start the server

The server starts automatically when used with Claude Desktop. Ensure that Claude Desktop is configured to detect the MCP server.

Example workflow

1. Claude receives a query requiring advanced inference.
2. The query is forwarded to DeepSeek R1 for processing.
3. DeepSeek R1 returns structured inference content wrapped in <ant_thinking> tags.
4. Claude integrates the inference results into the final response.

📄 License

This project is released under the MIT License. For more details, see the LICENSE file.