DeepSeek MCP server for AI agents

The DeepSeek MCP Server provides code generation and completion capabilities using the DeepSeek API, with support for tool chaining and cost optimization. It offers a structured way to generate, complete, and optimize code through a standardized interface.

Installation

To get started with the DeepSeek MCP Server:

Clone the repository
Install dependencies:
```
npm install
```
Build the project:
```
npm run build
```

Configure your DeepSeek API key in the MCP settings file:

{
  "mcpServers": {
    "deepseek": {
      "command": "node",
      "args": ["/path/to/deepseek-mcp/build/index.js"],
      "env": {
        "DEEPSEEK_API_KEY": "your-api-key"
      }
    }
  }
}

Usage

The server works with any MCP-compatible client. Here's a basic example using the MCP CLI:

mcp use deepseek generate_code --params '{"prompt": "Write a hello world program", "language": "python"}'

Available Tools

Generate Code

Generate language-specific code using the DeepSeek API:

{
  "name": "generate_code",
  "params": {
    "prompt": "Write a function that sorts an array",
    "language": "typescript",
    "temperature": 0.7
  }
}

Complete Code

Get intelligent code completions based on existing context:

{
  "name": "complete_code",
  "params": {
    "code": "function processData(data) {",
    "prompt": "Add input validation and error handling",
    "temperature": 0.7
  }
}

Optimize Code

Optimize existing code for performance, memory usage, or readability:

{
  "name": "optimize_code",
  "params": {
    "code": "your code here",
    "target": "performance"
  }
}

Execute Chain

Chain multiple tools together in sequence, with context passing between steps:

{
  "name": "execute_chain",
  "params": {
    "steps": [
      {
        "toolName": "generate_code",
        "params": {
          "prompt": "Create a REST API endpoint",
          "language": "typescript"
        }
      },
      {
        "toolName": "optimize_code",
        "params": {
          "target": "performance"
        }
      }
    ]
  }
}

Tool Chaining Examples

You can create powerful workflows by chaining tools together. Each tool in the chain can access the results of previous tools:

{
  "steps": [
    {
      "toolName": "generate_code",
      "params": {
        "prompt": "Create a user authentication function",
        "language": "typescript"
      }
    },
    {
      "toolName": "complete_code",
      "params": {
        "prompt": "Add input validation and error handling"
      }
    },
    {
      "toolName": "optimize_code",
      "params": {
        "target": "security"
      }
    }
  ]
}

Cost Optimization Features

The server implements several strategies to optimize API costs:

Request caching with TTL
Chain result caching
Smart prompt construction
Metadata tracking for usage analysis

Requirements

Node.js >= 18.0.0
DeepSeek API key
MCP-compatible client

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.