Deepseek Thinker MCP Server

Name: Deepseek Thinker MCP Server
Author: ruixingshi

@ruixingshi

关于 Deepseek Thinker MCP Server

A MCP provider Deepseek reasoning content to MCP-enabled AI Clients, like Claude Desktop. Supports access to Deepseek's CoT from the Deepseek API service or a local Ollama server.

基本信息

分类

AI 与智能体

运行时

node

传输方式

stdio

发布者

ruixingshi

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "deepseek-thinker-mcp": {
      "command": "node",
      "args": [
        "build/index.js"
      ]
    }
  }
}

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 Thinker MCP Server?

Deepseek Thinker MCP Server is an MCP (Model Context Protocol) provider that delivers Deepseek reasoning content (including thought processes) to MCP-enabled AI clients, such as Claude Desktop. It supports access either through the Deepseek API service or via a local Ollama server.

How to use Deepseek Thinker MCP Server?

Install and run the server via npx -y deepseek-thinker-mcp or build locally with npm install && npm run build then run node build/index.js. Configure it in your client’s MCP settings, e.g., claude_desktop_config.json, setting environment variables for either OpenAI API mode (API_KEY, BASE_URL) or Ollama mode (USE_OLLAMA=true). Invoke the get-deepseek-thinker tool, providing an originPrompt string, to receive structured reasoning output.

Key features of Deepseek Thinker MCP Server

Dual mode support: OpenAI API and Ollama local
Captures Deepseek’s thinking process for reasoning output
Provides a single get-deepseek-thinker tool for reasoning queries
Built with TypeScript, @modelcontextprotocol/sdk, and Zod validation
Licensed under MIT

Use cases of Deepseek Thinker MCP Server

Integrating Deepseek reasoning directly into Claude Desktop conversations
Accessing Deepseek’s thought processes without sending data to the cloud (Ollama mode)
Adding reasoning capabilities to any MCP‑enabled AI assistant
Experimenting with Deepseek’s reasoning chain for analysis or debugging

FAQ from Deepseek Thinker MCP Server

I see “MCP error -32001: Request timed out”. What does that mean?

This error occurs when the Deepseek API response is too slow or the reasoning output is too long, causing the MCP server to time out.

What modes does Deepseek Thinker MCP Server support?

It supports two modes: OpenAI API mode (requires API_KEY and BASE_URL) and Ollama local mode (set USE_OLLAMA=true).

How do I switch between modes?

Set the appropriate environment variables in your MCP server configuration. Use API_KEY and BASE_URL for OpenAI API mode, or set USE_OLLAMA=true for Ollama mode.