DeepSeek MCP Server

What is DeepSeek MCP Server about?

Provides a proxy server that exposes DeepSeek's advanced language models (R1 and V3) through the Model Context Protocol, allowing tools like Claude Desktop to interact with them without exposing the API key directly.

How to use DeepSeek MCP Server?

Install the package globally or via Smithery:

npm install -g deepseek-mcp-server
# or via Smithery
npx -y @smithery/cli install @dmontgomery40/deepseek-mcp-server --client claude

Add a server entry to claude_desktop_config.json:

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

Run the server (or let Claude Desktop launch it) and start chatting.

Key features of DeepSeek MCP Server

Automatic fallback from R1 (deepseek-reasoner) to V3 (deepseek-chat) if the primary model is unavailable.
Dynamic model and configuration discovery via model-config and models resources.
Full control of temperature, max tokens, top‑p, presence and frequency penalties.
Multi‑turn conversation support with persistent context and settings.
Easy testing with the MCP Inspector tool.

Use cases of DeepSeek MCP Server

Training data generation: Capture multi‑turn dialogues for fine‑tuning custom DeepSeek models.
Complex problem solving: Maintain reasoning state across several exchanges.
Interactive troubleshooting: Provide step‑by‑step assistance while preserving context.
General purpose chat: Leverage the recommended V3 model for everyday interactions.

FAQ from the DeepSeek MCP Server

Q: Which model is used by default? A: The server starts with the R1 model (deepseek-reasoner). If it fails, it switches to V3 (deepseek-chat).
Q: How do I change the model during a conversation? A: Simply include a natural language command like “use deepseek-chat” or “switch to deepseek-reasoner”.
Q: Do I need to rebuild the project to change settings? A: No. All configuration changes are handled at runtime through the MCP interface.
Q: Can I test the server locally? A: Yes. Build with npm run build and run with the MCP Inspector:
```
npx @modelcontextprotocol/inspector node ./build/index.js
```

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

{ "mcpServers": { "deepseek": { "command": "npx", "args": [ "-y", "deepseek-mcp-server" ], "env": { "DEEPSEEK_API_KEY": "<YOUR_API_KEY>" } } } }

DeepSeek MCP Server