Movie Booking Assistant
Provides a suite of tools for searching movies, checking showtimes, and managing ticket bookings for Bangalore cinemas. It enables AI clients to handle end-to-end movie theater interactions including seat availability checks and reservation management.
README
Movie Booking Assistant
A demo movie booking system for Bangalore cinemas, built to showcase two ways of integrating AI with a Python backend:
- Gemini chat — a terminal chatbot powered by Google Gemini with function calling
- MCP server — exposes the same APIs as tools for MCP-compatible AI clients (e.g. Claude)
Project Structure
demo1/
├── api_v1.py # Movies & Showtimes API
├── api_v2.py # Bookings API
├── api_v3.py # Theatres & Seats API
├── chat.py # Gemini AI terminal chatbot
└── mcp_server.py # MCP server (for Claude / other MCP clients)
API Files
| File | Responsibility | Key Functions |
|---|---|---|
api_v1.py |
Movies & showtimes | search_movies, get_movie_details, get_showtimes |
api_v2.py |
Bookings | book_tickets, cancel_booking, get_booking_details, list_user_bookings |
api_v3.py |
Theatres & seats | list_theatres, get_theatre_details, check_seat_availability |
All data is hardcoded in-memory — no database required.
How It Works
Gemini Chat (chat.py)
You type a message
→ Sent to Gemini API
→ Gemini picks a tool to call (based on function docstrings)
→ Your code runs the function locally
→ Result sent back to Gemini
→ Gemini replies in plain English
Gemini never runs your code directly. It reads the function name, parameters, and docstring to decide what to call — your code executes it and reports back.
MCP Server (mcp_server.py)
FastMCP automatically converts each FastAPI app into MCP tools, namespaced as movies_*, bookings_*, and theatres_*. An MCP-compatible client (like Claude Code) connects to the server and calls tools the same way Gemini does — but over the MCP protocol instead.
Setup
1. Install dependencies
pip install -r requirements.txt
2. Set your Gemini API key
Create a .env file in the project root:
GEMINI_API_KEY=your_key_here
Get a key at aistudio.google.com.
Usage
Run the Gemini chatbot
python chat.py
Example interaction:
You: What sci-fi movies are showing today?
[calling tool: search_movies with {'genre': 'Sci-Fi'}]
Gemini: There are two sci-fi movies showing today — Inception and The Matrix...
You: Book 2 tickets for Inception at PVR Orion Mall
[calling tool: get_showtimes with {'movie_id': 'MOVIE-003'}]
[calling tool: book_tickets with {'showtime_id': 'SHOW-001', 'seats': 2, 'user_name': 'Joshua'}]
Gemini: Done! I've booked 2 tickets for Inception...
Type quit or exit to stop.
Run the MCP server
python mcp_server.py
Then connect any MCP-compatible client to it. For Claude Code, add it to your MCP settings pointing to this script.
Data Overview
- 10 movies — including Inception, The Matrix, Oppenheimer, and more
- 10 theatres — across Bangalore (PVR, INOX, Cinepolis)
- 15 showtimes — across 2 days, with 2D and IMAX options
- 3 pre-existing bookings — for user "Joshua"
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.