About
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
Installing Wwo
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/WorldWeatherOnline/wwo-mcpFAQ
Is Wwo MCP free?
Yes, Wwo MCP is free — one-click install via Unyly at no cost.
Does Wwo need an API key?
No, Wwo runs without API keys or environment variables.
Is Wwo hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Wwo in Claude Desktop, Claude Code or Cursor?
Open Wwo on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by 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
by xuzexin-hzCompare Wwo with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
