mcpField
D
Deepseek Reasoner

Deepseek Reasoner

Local
github.com/comeonzhjAI & Agents5Updated 81w ago

About Deepseek Reasoner

Have a think is an MCP server that calls the DeepSeek reasoning model for AI assistants needing additional reasoning. It requires a DeepSeek API key and runs as a Python script.

Key features

  1. 01Call the DeepSeek reasoning model
  2. 02Configure API key through an environment file
  3. 03Run as a Python script

Use cases

  1. 01Request additional reasoning for complex questions
  2. 02Call DeepSeek from an MCP client

MCP support

The MCP server makes DeepSeek reasoning available to compatible MCP clients. The README shows configuration examples for Claude, Windsurf, Cursor, and 5ir.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Have a think MCP Server

English|中文

全程由 Claude 构建,相关提示词参考how-to-prompt

如何使用

  1. 确保已经安装了 python 3.10+
  2. clone 仓库
git clone https://github.com/comeonzhj/have-a-think.git
  1. 安装依赖
pip install "mcp[cli]" httpx python-dotenv
  1. 创建一个 .env 文件保存你的 DeepSeek API key:
DEEPSEEK_API_KEY=your_deepseek_api_key_here

你可以从 DeepSeek's website 获取 DeepSeek 的 Key

直接运行服务:

python have-a-think.py

安装到 Claude / windsurf / cursor / 5ir 等客户端:

{
    "mcpServers": {
      "deepseek-reasoner": {
        "command": "python",
        "args": [
          "/path/to/have-a-think/have-a-think.py"
        ],
        "env": {
          "DEEPSEEK_API_KEY": "your_deepseek_api_key_here"
        }
      }
    }
  }

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.