MCP Server Taiwan Weather

🚀 Taiwan Weather - Central Weather Bureau MCP Server (Unofficial)

This is a Model Context Protocol (MCP) Server used to obtain data from the Taiwan Central Weather Bureau API. It provides a standardized way to connect AI models to the weather data source of the Central Weather Bureau.

🚀 Quick Start

Before using this MCP server, you need to obtain the API authorization code from the Taiwan Central Weather Bureau. Then, configure it according to the application you are using, such as Claude Desktop.

✨ Features

• Obtain weather forecast data for various cities and counties in Taiwan - 36 - hour weather forecast for today and tomorrow.

📦 Installation

Taiwan Central Weather Bureau API Authorization Code

You must first obtain the API authorization code from the Taiwan Central Weather Bureau:

• Go to https://opendata.cwa.gov.tw/user/authkey (you need to log in. If you don't have an account, please register).
• Click the "Get Authorization Code" button.
• Copy the authorization code.

For Claude Desktop or Other MCP - Supported Applications

To use it in Claude Desktop, add the following content to your claude_desktop_config.json:

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

If you want to use it in other MCP - supported applications, please refer to the configuration file of that application.

Windows npx Issue

If you cannot run the MCP Server using npx on Windows, you can try one of the following methods:

Use cmd to Execute npx

Configure to use cmd to execute npx:

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

Use node to Execute

Globally install @gonetone/mcp-server-taiwan-weather:

npm install -g @gonetone/mcp-server-taiwan-weather

Then configure to use node to execute:

{
  "mcpServers": {
    "taiwan-weather": {
      "command": "node",
      "args": [
        "<your-path>/node_modules/@gonetone/mcp-server-taiwan-weather"
      ],
      "env": {
        "CWA_API_KEY": "<Your Central Weather Bureau API Authorization Code>"
      }
    }
  }
}

You can use the npm root -g command to view the path of the globally installed node_modules directory.

💻 Usage Examples

Obtain weather forecast data for various cities and counties in Taiwan - 36 - hour weather forecast for today and tomorrow

• How's the weather in Kaohsiung today?
• I want to know the weather in Pingtung.
• Weather forecast for Taipei.

📚 Documentation

What is Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how applications provide context for large language models (LLMs). You can think of MCP as the USB - C interface for AI applications. Just as USB - C provides a standardized way for your devices to connect to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

For a detailed introduction, please refer to the official page of Model Context Protocol.

📄 API Documentation

Tools

1. get_taiwan_weather_forecast
   • Obtain weather forecast data for various cities and counties in Taiwan - 36 - hour weather forecast for today and tomorrow.
   • Input parameters:
     • locationName (string): Name of the city or county in Taiwan.
   • Return value: Json data (key records) from the Central Weather Bureau API F - C0032 - 001.

🔧 Technical Details

Build

yarn build

Test

You can use MCP Inspector to test the MCP Server:

npx -y @modelcontextprotocol/inspector -e CWA_API_KEY={Your Central Weather Bureau API Authorization Code} node .

For more details, please refer to the official page of MCP Inspector.

📄 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.