Hotels MCP Server
A Model Context Protocol (MCP) server that allows LLMs to search for hotels and destinations using the Booking.com API.
README
Hotels MCP Server
A Model Context Protocol (MCP) server that allows LLMs to search for hotels and destinations using the Booking.com API.
Features
- Search for destinations by name
- Get hotel listings for specific destinations with dates
- Rich hotel information including:
- Room details and types
- Pricing and discounts
- Ratings and reviews
- Photos
- Check-in/check-out times
- Star ratings
API Integration
This MCP server uses the Booking.com API via RapidAPI. You'll need:
- A RapidAPI account
- Subscribe to the Booking.com API
- Get your API key
The current implementation uses two endpoints:
/api/v1/hotels/searchDestination: Search for destinations/api/v1/hotels/searchHotels: Get hotels for a destination
Setup and Installation
Prerequisites
- Python 3.11+
- MCP SDK (
pip install mcp) - httpx (
pip install httpx) - python-dotenv (
pip install python-dotenv)
Installation
-
Clone this repository:
git clone https://github.com/username/hotels_mcp_server.git cd hotels_mcp_server -
Install dependencies:
pip install -r requirements.txt -
Configure your RapidAPI credentials:
- Copy
.env.exampleto.env - Add your RapidAPI key from Booking.com API on RapidAPI to the
.envfile
- Copy
Running the Server
Run the server with:
python main.py
The server uses stdio transport by default for compatibility with MCP clients like Cursor.
Using with MCP Clients
Cursor
-
Edit
~/.cursor/mcp.json:{ "hotels": { "command": "python", "args": [ "/path/to/hotels_mcp_server/main.py" ] } } -
Restart Cursor
-
Use natural language to search for hotels in Cursor:
- "Find hotels in Paris for next week"
- "What are the best-rated hotels in Tokyo?"
MCP Inspector
Test your server with MCP Inspector:
npx @modelcontextprotocol/inspector python main.py
This opens an interactive UI where you can:
- View available tools
- Send test requests
- See server responses
Available Tools
-
search_destinations: Search for destinations by name- Parameter:
query- Destination name (e.g., "Paris", "New York")
- Parameter:
-
get_hotels: Get hotels for a destination- Parameters:
destination_id: Destination ID from search_destinationscheckin_date: Check-in date (YYYY-MM-DD)checkout_date: Check-out date (YYYY-MM-DD)adults: Number of adults (default: 2)
- Parameters:
Code Structure
main.py: The entry point for the serverhotels_mcp/: The core MCP implementation__init__.py: Package initializationhotels_server.py: MCP server implementation with tool definitions
License
MIT © Esa Krissa 2025
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.