Taiwan Weather

Provides access to Taiwan Central Weather Bureau weather data via MCP for location-based forecasts.

javascript

7

GitHub Stars

javascript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "gonetone-mcp-server-taiwan-weather": {
      "command": "npx",
      "args": [
        "-y",
        "@gonetone/mcp-server-taiwan-weather"
      ],
      "env": {
        "CWA_API_KEY": "<Your Central Weather Bureau API key>"
      }
    }
  }
}

This MCP server lets you access Taiwan's Central Weather Bureau API data through the Model Context Protocol, enabling your AI applications to fetch up-to-date weather forecasts for Taiwan. It standardizes how your AI tools request and receive weather data, making it easier to plug weather information into conversations and features.

How to use

To use this MCP server with an MCP client, connect your client to the Taiwan Weather MCP server and invoke the weather forecast tool as needed. The server exposes a tool that retrieves today and tomorrow’s 36-hour weather forecast for any Taiwan county or city. You will supply the location name, and the server returns the Central Weather Bureau API data in a consistent format for your AI workflow.

How to install

Prerequisites: you need Node.js and npm or yarn installed on your machine.

Install and run the MCP server locally by following these steps.

Install dependencies and run the server via npx as shown in the configuration snippet.

Additional setup and usage notes

API key: You must obtain a Central Weather Bureau API key from the official open data portal and set it in the environment variable CWA_API_KEY when starting the MCP server.

Examples and configuration

{
  "mcpServers": {
    "taiwan-weather": {
      "command": "npx",
      "args": [
        "-y",
        "@gonetone/mcp-server-taiwan-weather"
      ],
      "env": {
        "CWA_API_KEY": "<Your Central Weather Bureau API key>"
      }
    }
  }
}

Security and credentials

Treat your API key like a password. Do not hard-code it in public repositories. Use a secure environment variable management approach when deploying the MCP server.

Troubleshooting tips

If you encounter issues starting the server, ensure the environment variable CWA_API_KEY is set correctly and that Node.js is available on your system. Check that the exact MCP command and arguments appear as shown in the configuration examples.

Notes on alternative run methods

If you are on Windows and run into npx execution problems, you can switch to cmd to invoke npx or install the MCP server globally and run it through node. The following alternative configurations illustrate these approaches.

Tools

The server provides a weather forecast tool that returns today and tomorrow’s 36-hour weather forecast data for specified Taiwan locations. You input the locationName and you receive the Central Weather Bureau API data in a structured response.

Available tools

get_taiwan_weather_forecast

Retrieve Taiwan city and county weather forecasts for today and the next 36 hours.