Hotel Booking MCP Server
An MCP server that connects AI assistants like Claude to a Microsoft SQL Server hotel booking database, exposing tools to query customers, rooms, and bookings.
README
🏨 Hotel Booking MCP Server
An MCP (Model Context Protocol) server that connects AI assistants like Claude to a Microsoft SQL Server hotel booking database. It exposes hotel data as tools that Claude can call naturally in conversation.
📋 Features
| Tool | Description |
|---|---|
get_all_customers |
Fetch all registered customers |
get_all_rooms |
Fetch all rooms with full details |
get_available_rooms |
Fetch only rooms with Available status |
get_all_bookings |
Fetch all bookings with customer & room info |
get_active_bookings |
Fetch only Confirmed and Pending bookings |
🛠️ Tech Stack
- Python 3.12+
- MCP Python SDK v2.0.0 (
mcp) - pyodbc — Microsoft SQL Server driver
- uv — Fast Python package & project manager
- SQL Server with ODBC Driver 17
⚙️ Prerequisites
- Python 3.12+ installed
- uv installed — Install uv
- ODBC Driver 17 for SQL Server installed — Download here
- SQL Server running locally with the
HotelBookingSystemdatabase
🗄️ Database Setup
The server connects to a local SQL Server database using Windows Authentication (Trusted Connection).
Connection string used:
Driver={ODBC Driver 17 for SQL Server}
Server=localhost
Database=HotelBookingSystem
Trusted_Connection=yes
Required tables:
Customers— CustomerID, FirstName, LastName, Email, PhoneNumber, City, CountryRooms— RoomID, RoomNumber, RoomType, Floor, Capacity, PricePerNight, Amenities, StatusBookings— BookingID, CustomerID, RoomID, CheckInDate, CheckOutDate, TotalPrice, BookingStatus, PaymentStatus
🚀 Getting Started
1. Clone the repository
git clone <your-repo-url>
cd HotelBookingMCP
2. Create virtual environment and install dependencies
uv sync
3. Run the MCP server (stdio mode)
uv run python main.py
4. Test with the MCP Inspector
uv run mcp dev main.py
Then open the URL shown in the terminal (e.g. http://localhost:6274) in your browser.
🤖 Connecting to Claude Desktop
Option A — Automatic install (recommended)
uv run mcp install main.py
Option B — Manual config
Edit %APPDATA%\Claude\claude_desktop_config.json and add:
{
"mcpServers": {
"Hotel Booking MCP Server": {
"command": "C:\\Users\\<YOUR_USERNAME>\\.local\\bin\\uv.EXE",
"args": [
"run",
"--project",
"D:\\Path\\To\\HotelBookingMCP",
"python",
"D:\\Path\\To\\HotelBookingMCP\\main.py"
]
}
}
}
⚠️ Replace
<YOUR_USERNAME>and the paths with your actual values.
After updating the config, fully restart Claude Desktop for the changes to take effect.
🔧 Connecting to Claude Code (CLI)
claude mcp add hotel-booking-mcp -- uv run python main.py
📁 Project Structure
HotelBookingMCP/
├── main.py # MCP server with all tools
├── pyproject.toml # Project metadata & dependencies
├── .python-version # Python version pin
├── .gitignore
└── README.md
📝 Example Claude Prompts
Once connected, you can ask Claude things like:
- "Show me all available rooms"
- "List all active bookings"
- "Which customers are from Yangon?"
- "What rooms are available and what are their prices?"
🪪 License
MIT
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。