Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Wheather

FreeNot checked

Provides real-time weather information for any location using the Open-Meteo API, enabling AI models to query current weather data through the Model Context Pro

GitHubEmbed

About

Provides real-time weather information for any location using the Open-Meteo API, enabling AI models to query current weather data through the Model Context Protocol.

README

A Model Context Protocol (MCP) server that provides real-time weather information using the Open-Meteo API.

📋 Description

This project implements an MCP server that allows AI models to obtain current weather information for any location worldwide. The server uses Open-Meteo's free APIs for geocoding and weather data.

🔍 Documentation

Check out the documentation for more details on how to work with this server.

✨ Features

  • 🌍 Global coverage: Get weather information from any location worldwide
  • 🔄 Real-time data: Up-to-date weather information
  • 📊 Complete data: Temperature, humidity, precipitation, wind, cloud cover
  • 🚀 Fast and efficient: Quick responses with structured JSON data
  • 🔧 Easy integration: Compatible with any MCP client

🛠️ Installation

Prerequisites

  • Bun (recommended) or Node.js 20+

Installation Steps

  1. Clone the repository

    git clone https://github.com/zkjon/mcp-weather.git
    cd mcp-weather
    
  2. Install dependencies

    bun install
    # or
    npm install
    
  3. Run the server

    bunx -y tsx src/main.ts
    # or
    npx -y tsx src/main.ts
    

🚀 Usage

MCP Configuration

To use this server with an MCP client, add the following configuration to your mcp.json file:

{
    "mcpServers": {
        "Weather": {
            "command": "bunx",
            "args": [
                "-y",
                "tsx",
                "C:\\full\\path\\to\\project\\src\\main.ts"
            ]
        }
    }
}

Available Tools

get-weather

Gets weather information for a specific location.

Parameters:

  • location (string): Location name (city, country, etc.)

Usage Example:

// Request
{
    "tool": "get-weather",
    "arguments": {
        "location": "Madrid"
    }
}

// Response
{
    "content": [
        {
            "type": "text",
            "text": "{
                \"latitude\": 40.4375,
                \"longitude\": -3.6875,
                \"current\": {
                    \"temperature_2m\": 18.7,
                    \"relative_humidity_2m\": 54,
                    \"precipitation\": 0,
                    \"rain\": 0,
                    \"cloud_cover\": 4,
                    \"wind_speed_10m\": 6.1
                }
            }"
        }
    ]
}

Workflow

  1. Request reception: Server receives a request with a location
  2. Geocoding: Location coordinates are obtained using Open-Meteo API
  3. Weather query: Weather data is queried using the coordinates
  4. Structured response: Data is returned in structured JSON format

Code Structure

  • Imports: MCP SDK and necessary libraries
  • Server configuration: MCP server definition with name and version
  • Tool definition: Implementation of the get-weather tool
  • Connection: Transport configuration and server connection

🌐 APIs Used

📝 License

This project is licensed under the MIT License. See the LICENSE file for more details.

🤝 Contributing

Contributions are welcome! Please read our contribution guide for more information.

🔒 Security

If you find any security vulnerability, please check our security file to know how to report it.

📞 Support

If you have questions or need help:

🙏 Acknowledgments


Made with ❤️ by zkjon

from github.com/zkjon/mcp-weather

Installing Wheather

This server has no published package — it is built from source. Open the repository and follow its README.

▸ github.com/zkjon/mcp-weather

FAQ

Is Wheather MCP free?

Yes, Wheather MCP is free — one-click install via Unyly at no cost.

Does Wheather need an API key?

No, Wheather runs without API keys or environment variables.

Is Wheather hosted or self-hosted?

A hosted option is available: Unyly runs the server in the cloud, no local setup required.

How do I install Wheather in Claude Desktop, Claude Code or Cursor?

Open Wheather 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

Compare Wheather with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All ai MCPs