What is an MCP Server?

An MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It simplifies the integration of AI with real-world information.

What data does the CWA MCP Server provide?

The server provides 3-day and 1-week weather forecasts for Taiwan counties and cities, as well as historical rainfall data for the past three days.

What weather elements are included in the forecasts?

The 3-day forecast includes temperature, humidity, wind speed, precipitation probability, and more. The 1-week forecast includes average, maximum, and minimum temperatures, UV index, and other elements.

How do I get an API key for the CWA API?

You need to request an API key from the Taiwan Central Weather Administration (CWA) through their Open Data Platform.

What are the system requirements for the CWA MCP Server?

The server requires Python 3.10+, MCP CLI 1.6.0+, and the uv package manager.

How do I install the CWA MCP Server?

You can install the server and its dependencies using uv pip install -e .

How do I start the CWA MCP Server?

You can start the server by executing uv --directory your_project_path run src/server.py your_API_key in your terminal or command prompt, replacing your_API_key with your actual API key.

What MCP tools are available with this server?

The server provides three main tools: get_3_days_weather, get_1_week_weather, and get_historical_rainfall.

Can I use this data for commercial purposes?

Yes, as long as you adhere to the terms and conditions of the Taiwan Central Weather Administration (CWA) Open Data Platform.

Does the server clean and format the data?

Yes, the server automatically cleans and converts the data into a consistent and easy-to-use format.