weather-mcp
Enables natural language queries for real-time weather and 16-day forecasts globally via Open-Meteo, with Chinese output and no API key needed.
README
weather-mcp
一个用于查询天气的 MCP(Model Context Protocol) 服务,基于免费的 Open-Meteo 接口实现。
✅ 无需 API Key ✅ 支持全球任意地点 ✅ 实时天气 + 未来 16 天预报 ✅ 中文输出
LLM 客户端(Claude Desktop、Cursor、Cline 等)接入后,就能直接用自然语言问"北京现在多少度""东京未来三天天气怎么样"。
✨ 功能
| 工具 | 说明 |
|---|---|
get_current_weather |
查询指定地点的实时天气(温度、体感、天气状况、湿度、风、观测时间) |
get_weather_forecast |
查询指定地点未来 1–16 天的逐日预报(天气、最高/最低温、降水) |
- 支持城市名(如
北京、Shanghai、Tokyo)或经纬度(如39.9,116.4) - 地点解析使用 Open-Meteo 地理编码接口,返回中文地名
- WMO 天气代码已映射为中文描述,风向转换为中文方位
📦 安装
要求 Python ≥ 3.10。
方式一:用 uv(推荐)
uv tool install weather-mcp
或直接从源码安装:
git clone https://github.com/your-username/weather-mcp.git
cd weather-mcp
uv pip install -e .
方式二:用 pip
git clone https://github.com/your-username/weather-mcp.git
cd weather-mcp
pip install -e .
也可以不安装、直接用 requirements.txt:
pip install -r requirements.txt
🔌 接入 MCP 客户端
Claude Desktop
编辑配置文件(macOS:~/Library/Application Support/Claude/claude_desktop_config.json,Windows:%APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"weather": {
"command": "weather-mcp"
}
}
}
如果是用 pip install -r requirements.txt 而非可编辑安装,请改用模块方式启动:
{
"mcpServers": {
"weather": {
"command": "python",
"args": ["-m", "weather_mcp"]
}
}
}
💡 在 VS Code / Cursor 中若使用
.venv,把command指向虚拟环境里的python或脚本路径即可。
Cursor / Cline / 其他支持 MCP 的客户端
配置方式类似,使用 stdio 传输,命令为 weather-mcp(或 python -m weather_mcp)。
🛠 本地开发
git clone https://github.com/your-username/weather-mcp.git
cd weather-mcp
# 创建虚拟环境并安装
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e .
# 以开发模式运行(带可视化调试界面)
mcp dev src/weather_mcp/server.py
# 直接启动 stdio 服务
python -m weather_mcp
项目结构
weather-mcp/
├── pyproject.toml # 打包配置(hatchling)+ 入口脚本
├── requirements.txt # 运行依赖
├── README.md
├── LICENSE # MIT
├── .gitignore
└── src/
└── weather_mcp/
├── __init__.py
├── __main__.py # python -m weather_mcp 入口
├── server.py # MCP 服务与工具定义(FastMCP)
└── weather.py # Open-Meteo 接口封装与解析
📝 示例
接入后,你可以直接在对话里问:
- "北京现在天气怎么样?"
- "帮我查一下上海未来 5 天的天气预报"
- "39.9,116.4 当前温度是多少?"
📄 许可证
MIT © weather-mcp contributors
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.