deepseek MCP server

Local 2025-08-31 23:15:42 0
Developer Tools @moyu6027/deepseek-MCP-server

A server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine to tackle complex reasoning tasks.

DeepSeek MCP Server

? Features

Enhance Claude's reasoning capabilities with the integration of DeepSeek R1's advanced reasoning engine. This server enables Claude to tackle complex reasoning tasks by leveraging the reasoning capabilites of deepseek r1 model.

  • DeepSeek R1 (The Brain) acts as the advanced reasoning planner:

  • Plans multi-step logical analysis strategies

  • Structures cognitive frameworks
  • Evaluates confidence and uncertainty
  • Monitors reasoning quality

  • Detects edge cases and biases

  • Claude (The Executor) implements the reasoning plans:

  • Executes the structured analysis

  • Implements planned strategies
  • Delivers final responses
  • Handles user interaction
  • Manages system integrations

? Features

Advanced Reasoning Capabilities

  • Supports intricate multi-step reasoning tasks.
  • Designed for precision and efficiency in generating thoughtful responses.
  • 使用无问芯穹的API

Complete Setup guide

Prerequisites

  • Python 3.12 or higher
  • uv package manager

  • INFINI_API_KEY For DeepSeek (Sign up at 无问芯穹)

  • Clone the Repository 

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

  • Ensure UV is Set Up

  • Windows: Run the following in PowerShell: 
    powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

  • Mac: Run the following: 

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

  • Create Virtual Environment 

    uv venv
source .venv/bin/activate

  • Install Dependencies 

    uv add "mcp[cli]" httpx

  • Set Up API Key 

    echo "INFINI_API_KEY=your_key_here" > .env

  • Install the Server 

    mcp install server.py -f .env

  • Configure MCP Server Edit the claude_desktop_config.json file to include the following configuration:

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

? Usage

Starting the Server

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

Example Workflow

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

? License

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

[
  {
    "description": "n    Process a query using DeepSeek's R1 reasoning engine and prepare it for integration with DeepSeek V3 or claude.nn    DeepSeek R1 leverages advanced reasoning capabilities that naturally evolved from large-scale n    reinforcement learning, enabling sophisticated reasoning behaviors. The output is enclosed n    within `<ant_thinking>` tags to align with V3 or Claude's thought processing framework.nn    Args:n        query (dict): Contains the following keys:n            - context (str): Optional background information for the query.n            - question (str): The specific question to be analyzed.nn    Returns:n        str: The reasoning output from DeepSeek, formatted with `<ant_thinking>` tags for seamless use with V3 or Claude.n    ",
    "inputSchema": {
      "properties": {
        "query": {
          "title": "Query",
          "type": "object"
        }
      },
      "required": [
        "query"
      ],
      "title": "reasonArguments",
      "type": "object"
    },
    "name": "reason"
  }
]