Deepseek R1 MCP Server

Name: Deepseek R1 MCP Server
Author: MCP-Mirror

@MCP-Mirror

代码仓库

关于 Deepseek R1 MCP Server

Mirror of

#mcp-server #deepseek #language-model

基本信息

分类

其他

传输方式

stdio

发布者

MCP-Mirror

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "66julienmartin_MCP-server-Deepseek_R1": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@66julienmartin/mcp-server-deepseek_r1",
        "--client",
        "claude"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Deepseek R1 MCP Server?

A Model Context Protocol (MCP) server implementation for the Deepseek R1 language model, optimized for reasoning tasks with an 8192‑token context window. It integrates with Claude Desktop and supports both DeepSeek‑R1 and DeepSeek‑V3 models.

How to use Deepseek R1 MCP Server?

Install via Smithery (npx -y @smithery/cli install @66julienmartin/mcp-server-deepseek_r1 --client claude) or manually by cloning the repository, running npm install, setting up a .env file with your Deepseek API key, then building (npm run build). Configure Claude Desktop to point to the built index.js and set the DEEPSEEK_API_KEY environment variable.

Key features of Deepseek R1 MCP Server

Advanced text generation with 8192‑token context window.
Configurable parameters: max_tokens and temperature.
Robust error handling with detailed messages.
Full MCP protocol support.
Claude Desktop integration.
Supports both DeepSeek‑R1 and DeepSeek‑V3 models.

Use cases of Deepseek R1 MCP Server

Code generation and mathematical reasoning.
Data cleaning and data analysis.
General conversation and dialogue.
Language translation.
Creative writing and poetry.

FAQ from Deepseek R1 MCP Server

Which models are supported?

The server defaults to DeepSeek‑R1 (deepseek-reasoner). You can switch to DeepSeek‑V3 (deepseek-chat) by modifying the model name in src/index.ts.

What are the runtime requirements?

Node.js v18 or higher, npm, Claude Desktop, and a valid Deepseek API key.

How do I configure the API key?

Copy .env.example to .env and add your key as DEEPSEEK_API_KEY=your-api-key-here. Also set this environment variable in the Claude Desktop server configuration.

What does the `temperature` parameter do?

It controls randomness. Default is 0.2. Recommended values: 0.0 for coding/math, 1.0 for data analysis, 1.3 for general conversation/translation, 1.5 for creative writing.