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"
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。