# mcp-server-taiwan-weather

Supplies AI models with 36-hour Taiwan weather forecasts from the official CWA open data API. Useful for regional trip planning or location-aware assistant prompts.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 11
- Author: GoneTone
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/GoneTone/mcp-server-taiwan-weather
- Updated: 2025-09-21
- HTML: https://affpapa.org/en/nevibecode/mcp/mcp-server-taiwan-weather

## What it does

This MCP server connects your coding agent to Taiwan's Central Weather Administration open data platform. It exposes a single tool called `get_taiwan_weather_forecast`. When the model passes a target county or city string in `locationName`, the server retrieves the `F-C0032-001` dataset payload for that area.

Access requires an authorization key from `opendata.cwa.gov.tw`. Without setting `CWA_API_KEY` in your environment, the server will not return any forecast data.

On Windows systems, launching via `npx` can sometimes fail. You can bypass this by executing `cmd /c npx` in the MCP configuration or installing the package globally with `npm` to run it directly through `node`.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `CWA_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add mcp-server-taiwan-weather -e CWA_API_KEY=<CWA_API_KEY> -- npx -y @gonetone/mcp-server-taiwan-weather
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add mcp-server-taiwan-weather --env CWA_API_KEY=<CWA_API_KEY> -- npx -y @gonetone/mcp-server-taiwan-weather
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mcp-server-taiwan-weather": {
            "command": "npx",
            "args": [
                "-y",
                "@gonetone/mcp-server-taiwan-weather"
            ],
            "env": {
                "CWA_API_KEY": "<CWA_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mcp-server-taiwan-weather": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@gonetone/mcp-server-taiwan-weather"
            ],
            "env": {
                "CWA_API_KEY": "<CWA_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e CWA_API_KEY=<CWA_API_KEY> mcp-server-taiwan-weather npx -y @gonetone/mcp-server-taiwan-weather
```
Replace <…> with your own values

## When to use it
- fetch 36-hour weather forecasts for Taiwanese cities
- parse CWA dataset F-C0032-001 directly into agent context
- automate local weather reports for Taipei or Kaohsiung

## Example prompts
- Check the weather forecast for Taipei over the next 36 hours
- Call get_taiwan_weather_forecast for Kaohsiung
- What is the current weather outlook in Pingtung?

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40459
- [OpenWork MCP Gateway](https://affpapa.org/en/nevibecode/mcp/openwork-mcp-gateway.md) — MCP server · ★ 24271
- [Keploy](https://affpapa.org/en/nevibecode/mcp/keploy.md) — MCP server · ★ 18779
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [basebalance.cloud — x402 RPC & MCP gateway](https://affpapa.org/en/nevibecode/mcp/basebalancecloud-x402-rpc-mcp-gateway.md) — MCP server · ★ 7548

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md