mcp-server-demo
Provides tools for calculating math expressions and querying weather, demonstrating how to build an MCP server using FastMCP or raw SDK.
README
MCP Server 开发指南
项目结构
mcp-server-demo/
├── server_fastmcp.py # FastMCP 方式(推荐,简洁)
├── server_raw.py # 原生 SDK 方式(底层,灵活)
├── test_server.py # 测试脚本
└── README.md # 本文件
快速开始
# 1. 初始化环境(创建 venv + 安装依赖)
bash setup.sh
# 2. 运行测试
.venv/bin/python test_server.py # 测试 FastMCP 版本
.venv/bin/python test_server.py raw # 测试原生 SDK 版本
# 或者先激活 venv,之后直接用 python
source .venv/bin/activate
python test_server.py
两种开发方式对比
FastMCP(推荐入门)
- 用装饰器
@mcp.tool()自动从函数签名生成 JSON Schema - 参数类型从 type hints 自动推断
- docstring 自动变成工具描述
- 启动一行代码:
mcp.run()
原生 SDK(底层)
- 手动定义
inputSchema(JSON Schema 格式) - 手动实现
list_tools()和call_tool()两个处理函数 - 更接近协议本身,适合需要精细控制的场景
如何接入 Hermes
在 ~/.hermes/config.yaml 中添加:
mcp_servers:
demo:
command: "/home/ubuntu/mcp-server-demo/.venv/bin/python"
args: ["/home/ubuntu/mcp-server-demo/server_fastmcp.py"]
重启 Hermes 后,会自动发现并注册两个工具:
mcp_demo_calculate— 计算数学表达式mcp_demo_get_weather— 查询天气
MCP 协议通信流程
客户端 (Hermes) Server (你的代码)
| |
|-- initialize 请求 ------------->|
|<-- initialize 响应 -------------| (serverInfo, capabilities)
| |
|-- tools/list 请求 ------------->|
|<-- tools/list 响应 -------------| (工具名称 + inputSchema)
| |
|-- tools/call 请求 ------------->|
| (name + arguments) |
|<-- tools/call 响应 -------------| (TextContent 结果)
| |
核心概念
Tool 定义
每个工具需要:
- name: 唯一名称
- description: 描述(LLM 会读这个来决定什么时候用)
- inputSchema: JSON Schema 格式的参数定义
传输方式
- stdio: 通过 stdin/stdout 通信,Hermes 默认用这个
- HTTP/StreamableHTTP: 监听端口,适合远程调用
安全注意事项
- 不要在 tool 实现里做危险操作(直接执行用户输入的代码等)
- 使用参数校验(FastMCP 的 type hints 会自动校验)
- 敏感信息通过
env配置传入,不要硬编码
进阶话题
- Resources: 暴露可读取的数据源(文件、数据库等)
- Prompts: 预定义的提示词模板
- Sampling: Server 主动请求 LLM 做推理(需要客户端支持)
- 错误处理: 返回
isError: true的结果 - 进度通知: 长时间运行的工具可以发送进度更新
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.