DeepSeek-Claude

Integrates DeepSeek R1 reasoning with Claude to handle complex multi-step tasks via an MCP server.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-harshj23_deepseek-claude-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\ABSOLUTE\\PATH\\TO\\PARENT\\FOLDER\\deepseek-claude",
        "run",
        "server.py"
      ]
    }
  }
}

DeepSeek-Claude MCP Server enhances Claude’s reasoning by linking it with DeepSeek R1’s advanced reasoning engine. This MCP server enables Claude to handle complex, multi-step reasoning tasks with precision and efficiency, integrating structured reasoning results into Claude’s responses.

How to use

You use this MCP server by configuring Claude Desktop to load the DeepSeek-Claude MCP and then running the MCP locally. Once set up, Claude can offload advanced reasoning tasks to DeepSeek R1, receive structured reasoning, and deliver integrated responses.

How to install

Prerequisites you need before installation are Python 3.12 or higher and the uv package manager. You also need a DeepSeek API key.

Install and set up the MCP server using the following steps. Use the commands that fit your operating system.

Clone the repository and enter the project folder.

git clone https://github.com/harshj23/deepseek-claude-MCP-server.git
cd deepseek-claude-MCP-server

Additional setup and configuration

Ensure the UV toolchain is installed and available for command execution. Follow the platform-specific steps below to install UV.

# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

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

Create a virtual environment and install MCP dependencies

Create a virtual environment and activate it, then install the MCP CLI dependencies.

uv venv
# On Windows use: .venv\Scripts\activate
source .venv/bin/activate
uv add "mcp[cli]" httpx

Configure the MCP server in Claude Desktop

Provide your DeepSeek API key when prompted by the DeepSeek integration setup. Then configure the MCP server entry to point Claude Desktop to the local server, using the following configuration snippet.

{
  "mcpServers": {
      "deepseek-claude": {
          "command": "uv",
          "args": [
              "--directory",
              "C:\\ABSOLUTE\\PATH\\TO\\PARENT\\FOLDER\\deepseek-claude",
              "run",
              "server.py"
          ]
      }
  }
}

Run the server

Start the MCP server so Claude Desktop can communicate with it.

uv run server.py

Test setup and usage

Restart Claude Desktop to ensure the DeepSeek-Claude MCP is detected. Look for the tools icon in the interface to verify the integration. If the server does not appear, follow the troubleshooting steps specific to your setup to confirm the MCP server is reachable and correctly configured.