Duan Li MCP Weather Server Example

🚀 Weather Service MCP Server

A simple MCP project for weather service

🚀 Quick Start

📦 Installation

Claude Desktop Version

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 (brief/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-line 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/output, debugging can be challenging. For the best debugging experience, we highly recommend using MCP Inspector.

You can start the MCP Inspector with the following command:

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.