Terminal-based Chat Client with MCP Server Integration

Name: Terminal-based Chat Client with MCP Server Integration
Author: alan-meigs

@alan-meigs

代码仓库

关于 Terminal-based Chat Client with MCP Server Integration

MCP Client and Server Experiments

基本信息

分类

AI 与智能体

运行时

python

传输方式

stdio

发布者

alan-meigs

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "MCP_EXP": {
      "command": "uv",
      "args": [
        "init"
      ]
    }
  }
}

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 Terminal-based Chat Client with MCP Server Integration?

A terminal-based chat client that connects to an MCP server and integrates with OpenAI's API, including a weather service as an example of MCP functionality. It demonstrates how to build an extensible chat interface with tool execution.

How to use Terminal-based Chat Client with MCP Server Integration?

Install UV, create a virtual environment, install required packages (httpx, mcp[cli], openai, python-dotenv), set your OpenAI API key in a .env file, start the weather server (python weather.py), then run the chat client (python client.py weather.py). Optionally configure the server in Cursor’s Agent mode via Settings or a .cursor/mcp.json file.

Key features of Terminal-based Chat Client with MCP Server Integration

Real‑time chat interface with OpenAI integration
MCP server integration for extensible functionality
Weather service with alerts and forecasts
Asynchronous operation for better performance
Proper error handling and resource cleanup
Environment variable configuration for API keys

Use cases of Terminal-based Chat Client with MCP Server Integration

Chat with an AI assistant about general topics
Ask for current weather conditions in a US state or city
Retrieve active weather alerts for a given US state
Get detailed weather forecasts by latitude and longitude
Integrate the weather tools into Cursor’s Agent mode

FAQ from Terminal-based Chat Client with MCP Server Integration

What are the prerequisites to run the server?

Python 3.8 or higher and the UV package manager are required.

How do I get my OpenAI API key?

Create a .env file in the project root and add OPENAI_API_KEY=your_api_key_here.

Can I use this with Cursor?

Yes. The MCP server can be added in Cursor’s Agent mode (Composer) via Settings → Features → MCP, or by creating a .cursor/mcp.json file with the server command.