Описание
Wwo — Model Context Protocol server
README
MCP server for World Weather Online. Lets AI assistants like Claude, Cursor, and others call WWO weather data directly as tools.
Deploy to Railway
Step 1 — Push to GitHub
- Create a new repository on github.com (call it
wwo-mcp-server) - Open Terminal in this folder and run:
git init
git add .
git commit -m "Initial commit"
git remote add origin https://github.com/YOUR_USERNAME/wwo-mcp-server.git
git push -u origin main
Step 2 — Deploy on Railway
- Go to https://railway.app and sign up / log in with GitHub
- Click New Project → Deploy from GitHub repo
- Select your
wwo-mcp-serverrepository - Railway detects Node.js automatically and deploys
Your server will be live at a URL like:
https://wwo-mcp-server-production.up.railway.app
Step 3 — Add Custom Domain
In Railway dashboard → your project → Settings → Networking → Custom Domain
Type
mcp.worldweatheronline.comand click AddRailway shows you a CNAME value like:
wwo-mcp-server-production.up.railway.appGo to your DNS provider and add:
Type Name Value CNAME mcp wwo-mcp-server-production.up.railway.app SSL certificate is provisioned automatically within minutes
Step 4 — Test
Visit your health endpoint:
https://mcp.worldweatheronline.com/health
Test in MCP Inspector:
https://mcp.worldweatheronline.com/mcp?key=YOUR_WWO_API_KEY
Connecting AI Clients
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"world-weather-online": {
"url": "https://mcp.worldweatheronline.com/mcp?key=YOUR_API_KEY"
}
}
}
Cursor / Windsurf
Add to .cursor/mcp.json:
{
"mcpServers": {
"world-weather-online": {
"url": "https://mcp.worldweatheronline.com/mcp?key=YOUR_API_KEY"
}
}
}
Available Tools
| Tool | Description |
|---|---|
get_weather |
Current conditions + 14-day forecast |
get_historical_weather |
Past weather from 2008 onwards |
get_marine_weather |
Swell, tides, water temperature |
get_ski_weather |
Top/mid/base elevation forecasts |
search_location |
Location autocomplete |
get_astronomy |
Sunrise, sunset, moon phase |
get_timezone |
Local time + UTC offset |
get_climate_averages |
Monthly 12-year climate averages |
Local Development
npm install
npm run dev
Server runs at http://localhost:3000
Установка Wwo
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/WorldWeatherOnline/wwo-mcpFAQ
Wwo MCP бесплатный?
Да, Wwo MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Wwo?
Нет, Wwo работает без API-ключей и переменных окружения.
Wwo — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить Wwo в Claude Desktop, Claude Code или Cursor?
Открой Wwo на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare Wwo with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
