About 和风天气mcp服务
A HeWeather MCP server for clients querying weather data in China. It converts city names to locations and provides current conditions, forecasts, and alerts, with API credentials configured by the operator.
Key features
- 01Convert city names to locations
- 02Query current weather
- 03Forecasts from 3 to 30 days
- 04Hourly forecasts from 24 to 168 hours
- 05Query weather alerts
Use cases
- 01Resolve a city name for weather lookup
- 02Check a city's current weather
- 03Retrieve daily or hourly forecasts
- 04Check alerts for a location
MCP support
The server exposes location lookup, weather forecast, and alert tools to MCP clients. It requires a HeWeather API key and request domain.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README和风天气 MCP Server
简介
和风天气的 MCP server，目前支持国内的天气查询，包含有地理位置坐标查询，城市天气实时、每日天气、逐小时天气预报以及天气预警。
工具列表
-
获取城市位置信息
city_geo- 把城市名称转为天气查询使用的地理坐标信息
- 输入：city_name
- 输出：返回城市地理位置信息
-
每日天气预报
get_weather_by_day- 获取每日的天气预报
- 输入：day (需要查询的天数，支持 3d、7d、10d、15d、30d，最少3d，最多30d)
- 输入：location
-
24-168小时逐小时天气预报
get_weather_by_hours- 输入：hours （需要查询的小时数，支持 24h、72h、168h最少24d，最多168d）
- 输入：location
-
获取城市天气预报
city_weather- 输入：location
-
获取天气预警信息
weather_warning- 输入：location
快速开始
注册账号
- 在和风天气创建账号并登录
- 进入开发者控制台
- 创建项目，获取 api key和api domain
使用服务
服务是由 golang 开发，直接打包为二进制进行使用
进入到项目根目录执行 go build
根据需求打包为不同的平台
在 vscode 中使用
{
"mcpServers": {
"weather": {
"command": "C:/project/MCP/weather/weather.exe",
"args": [],
"env":{
"WEATHER_API_KEY":和风天气API key,
"WEATHER_HOST":和风天气请求的domain，每个用户的不一样
}
}
}
}
更新
| 版本 | 内容 | 时间 |
|---|---|---|
| v1.0.0 | 天气查询工具 | 2025年5月6日 |
Comments
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.