MCP Weather Server Example

🚀 Weather Service MCP Server

A simple MCP project for weather services

🚀 Quick Start

📦 Installation

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json%

✨ Features

Resources

The server implements a simple note storage system with the following features:

• A custom note:// URI scheme for accessing individual notes.
• Each note resource includes a name, description, and text/plain MIME type.

Prompts

The server provides a prompt:

• summarize-notes: Generate a summary of all stored notes.
  • An optional "style" parameter to control the level of detail (concise/detailed).
  • Generate a prompt containing all current notes based on style preferences.

Tools

The server implements a tool:

• add-note: Add a new note to the server.
  • Accept "name" and "content" as required string parameters.
  • Update the server state and notify the client of resource changes.

📚 Documentation

Build and Release

To prepare the distribution package:

1. Synchronize dependencies and update the lock file:

uv sync

2. Build the package distribution:

uv build

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You need to set your PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since the MCP server runs via standard input and output, debugging can be challenging. For the best debugging experience, we highly recommend using MCP Inspector.

You can start the MCP Inspector by executing the following command with npm:

npx @modelcontextprotocol/inspector uv --directory /Users/<your-user-name>/Codes/GitHub/weather_service run weather-service

After starting, the Inspector will display a URL that you can access in your browser to start debugging.