noopurtiwari01/python-based-mcp-server

Python-Based MCP Project

Note: This project was developed on a macOS machine. The package manager uv was installed using Homebrew:

brew install uv

uv is a fast Python package manager and build tool, designed as a drop-in replacement for pip and virtualenv. It enables quick environment setup and dependency management.

This project provides a set of tools exposed via a FastMCP server, allowing you to interact with public APIs for weather and books (Open Library) using simple tool calls.

Quickstart with uv and Virtual Environments

1. Initialize the project and create a virtual environment:

   uv init
   uv venv
   source .venv/bin/activate  # or 'source .venv/bin/activate.fish' for fish shell
   

2. Install dependencies:

   uv add "mcp[cli]" httpx
   

3. Run the MCP server in development mode:

   mcp dev main.py
   

Project Structure

• main.py — Entry point. Registers and exposes all tools via FastMCP.
• weather_tools.py — Contains weather-related tools using the Open-Meteo API.
• open_library_tools.py — Contains book and author tools using the Open Library API.
• defaults.py — Stores API base URLs and configuration.
• pyproject.toml — Project dependencies and metadata.

Registered Tools

Weather Tools (weather_tools.py)

• get_forecast(latitude: float, longitude: float): Get daily weather forecast for a location.
• get_location(city_name: str): Get location details (latitude, longitude, etc.) for a city.
• get_current_weather(latitude: float, longitude: float): Get current weather conditions for a location.

Open Library Tools (open_library_tools.py)

• search_books(query: str, author: str = ""): Search for books by title or author.
• get_book_details(olid: str): Get details for a book by its Open Library ID (OLID).
• get_author_details(author_id: str): Get details for an author by their Open Library Author ID.
• search_authors(name: str): Search for authors by name and get their Open Library Author IDs.

Adding More Tools

To add more APIs, create a new file (e.g., news_tools.py), define your tools, and register them in main.py using the same pattern.

---

References

• Model Context Protocol (MCP): Hands-On with Agentic AI (LinkedIn Learning)

Author: Noopur License: MIT