Weather

You run a Docker-based MCP server that exposes weather data through a standardized interface. This enables you to ask an MCP-enabled client to fetch current conditions and forecasts for any city, using a lightweight, isolated Python service inside Docker.

How to use

You use an MCP client to request weather data from the server. After you have the container running, you can ask your MCP client questions like the current weather for a city or a forecast. The server responds with temperature, conditions, and humidity for the requested location. You can integrate this into your AI workflows to enrich conversations with real-time weather data.

A typical usage pattern is to start the weather MCP service, then query it through your MCP client. Ensure the client is configured to connect to the local MCP endpoint provided by the Dockerized server. Once connected, you can request weather data for cities around the world and receive structured weather information as the response.

How to install

Prerequisites you need before installation are Docker Desktop, Claude Desktop (for using the MCP server), and Git to clone the repository.

Step 1: Clone the repository and enter the project folder.

git clone https://github.com/Pimmetjeoss/MCP_container.git
cd MCP_container

Step 2: Build the Docker image that contains the MCP weather server and all dependencies.

docker build -t mcp-server .

Step 3: Run the container to start the MCP weather server.

docker run -d --name mcp-weather-server mcp-server

Additional configuration and usage notes

Connect to Claude Desktop by adding an MCP server entry that runs the weather script inside the container. Use the following configuration in Claude Desktop settings to invoke the server from the running container.

{
  "mcpServers": {
    "weather": {
      "command": "docker",
      "args": ["exec", "-i", "mcp-weather-server", "python", "/app/weather.py"]
    }
  }
}

Docker and container management commands

You can monitor, stop, start, or rebuild the MCP weather server container with these commands.

docker logs mcp-weather-server

docker stop mcp-weather-server

docker start mcp-weather-server

docker rm -f mcp-weather-server

docker build -t mcp-server .
docker rm -f mcp-weather-server
docker run -d --name mcp-weather-server mcp-server

Troubleshooting

If the container won’t start, ensure Docker Desktop is running and the port or container name isn’t already in use by another process.

If Claude Desktop cannot connect to the MCP server, verify the container is running and check container logs. Also confirm the configuration path matches your operating system and restart Claude Desktop after any changes.

On Windows, run Docker Desktop as Administrator and ensure WSL2 is properly configured if you encounter permission issues.

Project structure

The project includes the following key files that support the MCP server functionality.

mcp_container/
├── Dockerfile              # Docker configuration
├── weather.py             # MCP server implementation
├── requirements.txt       # Python dependencies
├── README.md              # This file
├── QUICK_START.md        # Quick setup guide
└── MCP_CONTAINER_GUIDE.md # Detailed documentation

Tools and endpoints

The MCP server provides a weather data tool you can invoke from your MCP client.

Available tools

get-weather

Get current weather information for any city. Input: city (string). Output: Temperature (°C), conditions, and humidity (%).