DeepSeek

Provides a DeepSeek MCP server to access DeepSeek API models via MCP clients for chat completions and configurable parameters.

javascript

0

GitHub Stars

javascript

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-dmontgomery40_deepseek-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-mcp-server"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can run a DeepSeek MCP Server to bridge DeepSeek’s language models with MCP-compatible clients. This server lets you handle chat completions and model interactions through a simple, transport-agnostic interface, enabling you to connect clients like Claude Desktop and other MCP-enabled tools with your own DeepSeek API key.

How to use

To use the DeepSeek MCP Server, install it globally, provide your DeepSeek API key, and connect your MCP client to the server through a standard MCP transport. The server exposes a chat completion capability with configurable model selection, temperature, token limits, and sampling controls, so you can tailor responses for your applications. After starting the server, configure your MCP client to discover and communicate with it using the shared MCP protocol.

How to install

Prerequisites: Node.js and npm must be installed on your system.

Install the MCP server globally.

Set up your API key in the environment.

Start using the server with an MCP client by configuring the client to connect to the stdio-based MCP server.

Available tools

ChatCompletion

Chat completion tool with support for selecting a model, adjusting temperature, max tokens, Top P, presence penalty, and frequency penalty to shape responses.