DeepSeek MCP Server

What is DeepSeek MCP Server?

DeepSeek MCP Server is a Model Context Protocol (MCP) server designed to seamlessly integrate DeepSeek's advanced language models with MCP-compatible applications, such as Claude Desktop. It acts as a proxy, allowing users to anonymously leverage the DeepSeek API.

How to use DeepSeek MCP Server?

Installation

Via Smithery (for Claude Desktop):

npx -y @smithery/cli install @dmontgomery40/deepseek-mcp-server --client claude

Manual Installation:

npm install -g deepseek-mcp-server

Usage with Claude Desktop

Add the following configuration to your claude_desktop_config.json:

{
  "mcpServers": {
    "deepseek": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-mcp-server"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "your-api-key"
      }
    }
  }
}

Testing with MCP Inspector

Build the server:
```
npm run build
```

Run with MCP Inspector:

npx @modelcontextprotocol/inspector node ./build/index.js

Key Features of DeepSeek MCP Server

Anonymous DeepSeek API Usage: Functions as a proxy to obscure direct API calls.
Intelligent Request Handling: Maps natural language requests to configuration changes.
Automatic Model Fallback: Automatically switches from DeepSeek R1 (deepseek-reasoner) to DeepSeek V3 (deepseek-chat) if R1 is unavailable.
Resource Discovery: Allows querying for available models and configurations.
Configurable Parameters: Supports custom model selection, temperature control, max tokens limit, Top P sampling, presence penalty, and frequency penalty.
Enhanced Conversation Features:
- Multi-turn Conversation Support: Maintains complete message history and context, preserving configuration settings throughout conversations.
- Handles Complex Dialogue Flows: Manages follow-up chains and intricate interactions automatically.

Use Cases of DeepSeek MCP Server

Integration with MCP-compatible Applications: Primarily designed for seamless integration with applications like Claude Desktop.
Anonymous API Access: For users who prefer to use the DeepSeek API without direct exposure.
Training & Fine-tuning: Provides properly formatted conversation data essential for training high-quality dialogue models due to its multi-turn support.
Complex Interactions in Production: Manages longer conversations where context is crucial, such as multi-step reasoning problems, interactive troubleshooting, and detailed technical discussions.

FAQ about DeepSeek MCP Server

Q: What models are available?
- A: The server can show a list of available models and their capabilities via the models resource.
Q: What configuration options do I have?
- A: All available configuration options can be listed via the model-config resource.
Q: What is the current temperature setting?
- A: The server can display the current temperature setting.
Q: Can I switch between DeepSeek R1 and V3?
- A: Yes, you can switch between deepseek-reasoner (R1) and deepseek-chat (V3) at any time by specifying the desired model in your prompt.
Q: Which DeepSeek model is recommended for general use?
- A: DeepSeek V3 is recommended for general-purpose use, while R1 is better for more technical and complex queries due to its speed and token usage.

A Model Context Protocol (MCP) server for the DeepSeek API, allowing seamless integration of DeepSeek's powerful language models with MCP-compatible applications like Claude Desktop.

Anonymously use DeepSeek API -- Only a proxy is seen on the other side

Installation

Installing via Smithery

To install DeepSeek MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @dmontgomery40/deepseek-mcp-server --client claude

Manual Installation

npm install -g deepseek-mcp-server

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "deepseek": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-mcp-server"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "your-api-key"
      }
    }
  }
}

Features

Note: The server intelligently handles these natural language requests by mapping them to appropriate configuration changes. You can also query the current settings and available models:

User: "What models are available?"
- Response: Shows list of available models and their capabilities via the models resource.
User: "What configuration options do I have?"
- Response: Lists all available configuration options via the model-config resource.
User: "What is the current temperature setting?"
- Response: Displays the current temperature setting.
User: "Start a multi-turn conversation. With the following settings: model: 'deepseek-chat', make it not too creative, and allow 8000 tokens."
- Response: Starts a multi-turn conversation with the specified settings.

Automatic Model Fallback if R1 is down

If the primary model (R1) is down (called deepseek-reasoner in the server), the server will automatically attempt to try with v3 (called deepseek-chat in the server)

Note: You can switch back and forth anytime as well, by just giving your prompt and saying "use deepseek-reasoner" or "use deepseek-chat"

V3 is recommended for general purpose use, while R1 is recommended for more technical and complex queries, primarily due to speed and token usage

Resource discovery for available models and configurations:

Custom model selection
Temperature control (0.0 - 2.0)
Max tokens limit
Top P sampling (0.0 - 1.0)
Presence penalty (-2.0 - 2.0)
Frequency penalty (-2.0 - 2.0)

Enhanced Conversation Features

Multi-turn conversation support:

Maintains complete message history and context across exchanges
Preserves configuration settings throughout the conversation
Handles complex dialogue flows and follow-up chains automatically

This feature is particularly valuable for two key use cases:

Training & Fine-tuning: Since DeepSeek is open source, many users are training their own versions. The multi-turn support provides properly formatted conversation data that's essential for training high-quality dialogue models.
Complex Interactions: For production use, this helps manage longer conversations where context is crucial:
- Multi-step reasoning problems
- Interactive troubleshooting sessions
- Detailed technical discussions
- Any scenario where context from earlier messages impacts later responses

The implementation handles all context management and message formatting behind the scenes, letting you focus on the actual interaction rather than the technical details of maintaining conversation state.

Testing with MCP Inspector

You can test the server locally using the MCP Inspector tool:

Build the server:
```
npm run build
```

Run the server with MCP Inspector:

# Make sure to specify the full path to the built server
npx @modelcontextprotocol/inspector node ./build/index.js

The inspector will open in your browser and connect to the server via stdio transport. You can:

View available tools
Test chat completions with different parameters
Debug server responses
Monitor server performance

Note: The server uses DeepSeek's R1 model (deepseek-reasoner) by default, which provides state-of-the-art performance for reasoning and general tasks.

License

MIT

Login Required

Please log in to share your review and rating for this MCP.

DeepSeek MCP Server