About OpenWeather MCP Server
OpenWeather MCP Server provides MCP clients with current conditions and forecasts for locations worldwide. It accepts an API key through an environment variable or tool parameter and supports timezone offsets.
Key features
- 01Query weather worldwide
- 02Get current conditions and forecasts
- 03Return temperature, humidity, and wind
- 04Support timezone offsets
- 05Pass the API key by environment or parameter
Use cases
- 01Check current weather in a city
- 02Get a forecast for a location
- 03View weather using local time
MCP support
The MCP server exposes get_weather and get_current_weather tools for querying location-based weather and forecasts.
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 READMEOpenWeather MCP Server
English | 中文版
A simple weather forecast MCP (Model Control Protocol) server providing global weather forecasts and current weather conditions.
Screenshot of Claude Desktop using the MCP Weather Service
Features
- No separate configuration file needed; API key can be passed directly through environment variables or parameters
- Support for querying weather conditions anywhere in the world
- Provides current weather and future forecasts
- Detailed weather information including temperature, humidity, wind speed, etc.
- Support for different time zones
Installation Requirements
pip install mcp-server requests pydantic
Usage
1. Get an OpenWeatherMap API Key
Visit OpenWeatherMap and register an account to obtain an API key.
2. Run the Server
There are two ways to provide the API key:
Method 1: Using Environment Variables
# Set environment variables
export OPENWEATHER_API_KEY="your_api_key" # Linux/Mac
set OPENWEATHER_API_KEY=your_api_key # Windows
# Run the server
python weather_mcp_server.py
Method 2: Provide When Calling the Tool
Run directly without setting environment variables:
python weather_mcp_server.py
When calling the tool, you'll need to provide the api_key parameter.
3. Use in MCP Client Configuration
Add the following configuration to your MCP-supported client:
{
"weather_forecast": {
"command": "python",
"args": [
"/full_path/weather_mcp_server.py"
],
"env": {
"OPENWEATHER_API_KEY": "your_openweathermap_key_here"
},
"disabled": false,
"autoApprove": ["get_weather", "get_current_weather"]
}
}
4. Available Tools
get_weather
Get current weather and forecast for a specified location.
Parameters:
location: Location name, e.g., "Beijing", "New York", "Tokyo"api_key: OpenWeatherMap API key (optional, will read from environment variable if not provided)timezone_offset: Timezone offset in hours, e.g., 8 for Beijing, -4 for New York. Default is 0 (UTC time)
get_current_weather
Get current weather for a specified location.
Parameters:
location: Location name, e.g., "Beijing", "New York", "Tokyo"api_key: OpenWeatherMap API key (optional, will read from environment variable if not provided)timezone_offset: Timezone offset in hours, e.g., 8 for Beijing, -4 for New York. Default is 0 (UTC time)
Usage Example
AI assistant call example:
User: What's the weather like in New York right now?
AI: Let me check the current weather in New York for you.
[Calling get_current_weather("New York", timezone_offset=-4)]
Current weather in New York: 18°C, partly cloudy, humidity 65%, wind speed 3.5m/s.
Troubleshooting
If you encounter a "No API key provided" error, make sure:
- You have set the OPENWEATHER_API_KEY in environment variables, or
- You are providing the api_key parameter when calling the tools
If the location name is incorrect, you might receive a "Location not found" error. Try using a more accurate city name or add a country code, e.g., "Beijing,CN" or "Paris,FR".
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.