About Weather
A Caiyun (ColorfulClouds) Weather MCP server for users with access to its API. It provides current conditions, forecasts, historical weather and alerts, including air-quality measurements.
Key features
- 01Real-time weather and air quality
- 02Hourly forecasts for 72 hours
- 03Daily forecasts for 7 days
- 04Weather history for 24 hours
- 05Location-specific weather alerts
Use cases
- 01Check current conditions for a location
- 02Review hourly and weekly forecasts
- 03Inspect recent weather history
- 04Retrieve weather alerts and air-quality metrics
MCP support
The MCP server exposes five weather tools for real-time conditions, hourly and weekly forecasts, the past 24 hours of weather, and alerts. Each tool requires a valid Caiyun Weather API token in `CAIYUN_WEATHER_API_TOKEN`.
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 READMECaiyun Weather MCP Server
Setup Instructions
Before anything, ensure you have access to the API. You can apply for it at https://docs.caiyunapp.com/weather-api/.
Install uv first.
MacOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Setup with Claude Desktop
# claude_desktop_config.json
# Can find location through:
# Hamburger Menu -> File -> Settings -> Developer -> Edit Config
{
"mcpServers": {
"caiyun-weather": {
"command": "uvx",
"args": ["mcp-caiyun-weather"],
"env": {
"CAIYUN_WEATHER_API_TOKEN": "YOUR_API_KEY_HERE"
}
}
}
}
Ask Claude a question requiring weather
e.g. "What's the weather in Beijing Now?"
Local/Dev Setup Instructions
Setup with Claude Desktop
# claude_desktop_config.json
# Can find location through:
# Hamburger Menu -> File -> Settings -> Developer -> Edit Config
{
"mcpServers": {
"caiyun-weather": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/mcp-caiyun-weather",
"run",
"mcp-caiyun-weather"
],
"env": {
"CAIYUN_WEATHER_API_TOKEN": "YOUR_API_TOKEN_HERE"
}
}
}
}
Debugging
Run:
npx @modelcontextprotocol/inspector \
uv \
--directory /ABSOLUTE/PATH/TO/PARENT/FOLDER/mcp-caiyun-weather \
run \
mcp-caiyun-weather
Available Tools
-
get_realtime_weather: Get real-time weather data for a specific location- Parameters:
lng: The longitude of the locationlat: The latitude of the location
- Returns detailed information including:
- Temperature
- Humidity
- Wind speed and direction
- Precipitation intensity
- Air quality metrics (PM2.5, PM10, O3, SO2, NO2, CO)
- AQI (China and USA standards)
- Life indices (UV and Comfort)
- Parameters:
-
get_hourly_forecast: Get hourly weather forecast for the next 72 hours- Parameters:
lng: The longitude of the locationlat: The latitude of the location
- Returns hourly forecast including:
- Temperature
- Weather conditions
- Rain probability
- Wind speed and direction
- Parameters:
-
get_weekly_forecast: Get daily weather forecast for the next 7 days- Parameters:
lng: The longitude of the locationlat: The latitude of the location
- Returns daily forecast including:
- Temperature range (min/max)
- Weather conditions
- Rain probability
- Parameters:
-
get_historical_weather: Get historical weather data for the past 24 hours- Parameters:
lng: The longitude of the locationlat: The latitude of the location
- Returns historical data including:
- Temperature
- Weather conditions
- Parameters:
-
get_weather_alerts: Get weather alerts for a specific location- Parameters:
lng: The longitude of the locationlat: The latitude of the location
- Returns weather alerts including:
- Alert title
- Alert code
- Alert status
- Alert description
- Parameters:
Note: All tools require a valid Caiyun Weather API token to be set in the environment variable CAIYUN_WEATHER_API_TOKEN.
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.