Deepseek MCP server

This MCP server implementation enables Claude Desktop to interface with Deepseek models running in Docker. It provides a bridge between Claude Desktop and Deepseek's AI models, allowing you to leverage Deepseek's capabilities within your Claude environment.

Prerequisites

• Docker
• Python 3.11 or later
• A Deepseek API key
• Claude Desktop

Installation

Clone the Repository

git clone https://github.com/vincentf305/mcp-server-deepseek.git
cd mcp-server-deepseek

Install Dependencies

pip install -r requirements.txt

Setup Environment Variables

Create a .env file in the root directory of the project and add your Deepseek API key:

DEEPSEEK_API_KEY=your_api_key_here

Running the Server

You can run the MCP server either using Docker or locally on your machine.

Using Docker

1. Build the Docker image:

docker build -t mcp_server_deepseek .

2. Run the container:

docker run -d \
  --name mcp-server-deepseek \
  -p 8765:8765 \
  -e DEEPSEEK_API_KEY=your_api_key_here \
  mcp-server-deepseek

Running Locally

To start the server directly on your local machine:

python -m mcp_server_deepseek.server

Configuring Claude Desktop

1. Make sure you have your Deepseek API key ready

2. Add the following configuration to your Claude Desktop configuration file (claude_desktop_config.json):

{
  "mcpServers": {
    "deepseek-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "DEEPSEEK_API_KEY",
        "mcp_server_deepseek"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "your_api_key_here"
      }
    }
  }
}

3. Restart Claude Desktop to load the new configuration

Once configured, you'll be able to use Deepseek models directly within Claude Desktop through the MCP server connection.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.