How do I use Weather MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Weather MCP Server compare weather in London, Paris, and Berlin" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Weather MCP Server

A simple weather MCP server built with FastMCP that provides current weather data and city comparisons.

Features

Get current weather for any city
Compare weather between multiple cities
Support for metric and imperial units
Optional detailed forecasts

Quick Start

Installing via Smithery

To install Weather Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @glassBead-tc/weather-mcp --client claude

Manual Installation

Install dependencies:
pip install -r requirements.txt
Run locally:
python src/weather_server.py
Test with Claude Desktop/Code: Add to your MCP configuration:
{ "mcpServers": { "weather": { "command": "python", "args": ["/path/to/weather-mcp/src/weather_server.py"] } } }

Tools

get_weather

Get current weather for a city.

city (string): City name
units (string, optional): "metric" or "imperial" (default: "metric")
detailed (boolean, optional): Include 3-day forecast (default: false)

compare_weather

Compare weather between multiple cities (max 5).

cities (array): List of city names
metric (string, optional): Sort by "temperature", "humidity", or "wind" (default: "temperature")

Deploy to Smithery

Push to GitHub
Go to smithery.ai/new
Connect your repository
Deploy!

Example Usage

# Get weather for London await get_weather("London") # Get detailed weather with forecast await get_weather("Tokyo", units="imperial", detailed=True) # Compare temperatures across cities await compare_weather(["New York", "Los Angeles", "Chicago"], metric="temperature")

EOF < /dev/null