What are the runtime requirements?
Node.js 18 or higher is required. A valid CWA API key must be obtained from [https://opendata.cwa.gov.tw/user/authkey](https://opendata.cwa.gov.tw/user/authkey).
@lincw
基本信息
利用台灣中央氣象局的 API 建立 MCP-server
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"cwa": {
"command": "node",
"args": [
"/path/to/cwa-server.js"
],
"env": {
"CWA_API_KEY": ""
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A lightweight Node.js Model Context Protocol (MCP) server that connects Claude Desktop to the Taiwan Central Weather Administration (CWA) API, providing access to weather forecast data for all Taiwanese counties and cities.
Obtain a CWA API key from the official website, run the install.sh script, then edit the Claude Desktop configuration file (~/.config/claude/claude_desktop_config.json) to add your API key and server path. Restart Claude Desktop to start querying weather data. Docker deployment is also supported via docker-compose.yml.
get_weather_forecastNode.js 18 or higher is required. A valid CWA API key must be obtained from [https://opendata.cwa.gov.tw/user/authkey](https://opendata.cwa.gov.tw/user/authkey).
Edit `~/.config/claude/claude_desktop_config.json` and add the `cwa` MCP server entry with the `command`, `args` pointing to `cwa-server.js`, and the `CWA_API_KEY` environment variable.
Yes. A Docker Compose file is provided in the README. You set the `CWA_API_KEY` environment variable in `docker-compose.yml` and update the Claude Desktop configuration to use the `docker exec` command.
It retrieves a 36‑hour weather forecast for any supported Taiwanese county or city. The tool is named `get_weather_forecast`.
The server supports 22 locations: all special municipalities (Taipei, New Taipei, Taoyuan, Taichung, Tainan, Kaohsiung), counties (e.g., Yilan, Hualien, Taitung), and outlying islands (Penghu, Kinmen, Lienchiang).

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
MCP Toolbox for Databases is an open source MCP server for databases.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Hindsight: Agent Memory That Learns
评论