About Weather MCP Server
Weather MCP Server retrieves information from Malaysia's government open data API for LLMs that need local forecasts, warnings, water levels, and earthquake reports. Its tools support queries by location and date range.
Key features
- 01Retrieve weather forecasts
- 02Retrieve weather warnings
- 03Check flood-related water levels
- 04Fetch earthquake reports
Use cases
- 01Check a forecast for a location
- 02Search weather warnings by date range
- 03Check flood water levels by state or district
- 04Find earthquake reports by place and date range
MCP support
This MCP server exposes tools for querying forecasts, weather warnings, water levels, and earthquake reports from Malaysia's government open data API.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEWeather MCP Server
A basic Model Context Protocol (MCP) server that provides weather information retrieved from Open API of Malaysia's official open data portal. This server enables LLMs to get weather forecast, warnings, water level associated with flood, and earthquake reports.
API Documentation: data.gov.my
Components
Tools
-
get_water_level_condition
-
Retrieve the water level conditions associated with flood warnings for a specified district or state. If both district and state are provided, the district takes precedence. If district or state is not specified, use an empty string for that field.
-
Args:
- district: The name of the district within the specified state for which to retrieve flood warning conditions.
- state: The name of the state in Malaysia for which to retrieve flood warning conditions.
-
-
get_warning
-
Retrieve general weather warnings issued within a specified date range.
-
Args:
- datetime_start: The earliest timestamp in the form of
YYYY-MM-DD HH:MM:SS(inclusive) from which to retrieve weather warnings. If omitted, defaults to the current date. - datetime_end: The latest timestamp in the form of
YYYY-MM-DD HH:MM:SS(inclusive) to stop retrieving the weather warnings. If omitted, defaults to the current date.
- datetime_start: The earliest timestamp in the form of
-
-
get_weather_forecast
-
Retrieve a weather forecast for a specific location within a given date range.
-
Args:
- location_name: The name or identifier of the location for which the forecast is retrieved.
- date_start: The earliest date (inclusive) to begin retrieving the weather forecast. If omitted, defaults to the current date.
- date_end: The latest date (inclusive) to stop retrieving the weather forecast. If omitted, defaults to the current date.
-
-
get_earthquake_news
-
Fetch earthquake news for a given location within a specified date range.
-
Args:
- location: Name or identifier of the place where the earthquake(s) occurred.
- date_start: The earliest date (inclusive) to start searching for earthquake news. If omitted, defaults to the current date.
- date_end: The latest date (inclusive) to stop searching for earthquake news. If omitted, defaults to the current date.
-
Claude Desktop configuration
Add the following into claude_desktop_config.json file. For more information, refer to For Claude Desktop Users.
Using uv
{
"mcpServers": {
"weather": {
"command": "uv",
"args": [
"--directory",
"weather-my-mcp",
"run",
"weather.py"
]
}
}
}
Using Docker
-
Create docker image
docker build . --tag weather-my-mcp -
Edit
claude_desktop_config.jsonfile as follows:{ "mcpServers": { "weather": { "command": "docker", "args": [ "run", "-i", "--rm", "weather-my-mcp" ] } } }
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
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.