使用说明
FastMCP实施
使用FastMCP、Python 3.13和现代异步模式的生产就绪MCP（模型上下文协议）服务器和客户端实现。
这是什么？
此项目演示了如何构建 干净、可读的MCP服务器和客户端 使用FastMCP库。它包括：
- 3台生产MCP服务器 （天气、新闻、财经）
- 智能MCP客户端 与LLM集成（Anthropic/OpenAI）
- 交互式聊天界面 用于测试
- 自动化测试套件 用于验证
=€快速入门
1.安装依赖项
cd fastmcp-implementation
uv sync
2.配置API密钥
编辑 .env 使用API密钥文件：
# LLM Provider (required)
OPENAI_API_KEY=your_key_here
ANTHROPIC_API_KEY=your_key_here
# External APIs (optional - servers will work with test keys)
OPENWEATHER_API_KEY=your_key_here
NEWS_API_KEY=your_key_here
EXCHANGERATE_API_KEY=your_key_here
3.运行自动测试
uv run python examples/test_demo.py
预期产量：
======================================================================
TEST SUMMARY
======================================================================
[PASS] Weather Server
[PASS] News Server
[PASS] Finance Server
Total: 3/3 tests passed
======================================================================
4.尝试互动模式
uv run python examples/interactive_client.py
=Á项目结构
fastmcp-implementation/
�� server/ # MCP servers (Weather, News, Finance)
�� client/ # MCP client with LLM integration
�� examples/ # Interactive demo and tests
�� .env # API keys (gitignored)
�� pyproject.toml # UV dependencies
=à Tech Stack
- Python 3.13.1 - Latest Python release
- UV - Fast package manager
- MCP SDK 1.19.0 - Model Context Protocol
- Anthropic/OpenAI - LLM providers
- httpx - Async HTTP client
Success - All Tests Passed!
[PASS] Weather Server - 2 tools discovered
[PASS] News Server - 2 tools discovered
[PASS] Finance Server - 3 tools discovered
Total: 3/3 tests passed
See full documentation in FASTMCP_IMPLEMENTATION_PLAN.md
