MCP Amadeus

🚀 Amadeus MCP Server

Amadeus MCP Server is a community-developed Model Context Protocol (MCP) server that integrates the Amadeus Flight Offers Search API, providing flight search functionality through a natural language interface. It is suitable for MCP-compatible clients (e.g., Claude Desktop).

This project enables users to easily search for flight options between specific dates and locations, leveraging the power of large language models (LLMs) and the Amadeus API.

This project uses the official amadeus-python SDK

⚠️ Important Note

This project is open-source and is not affiliated with or endorsed by Amadeus IT Group. Amadeus® is a registered trademark of Amadeus IT Group.

🚀 Quick Start

📦 Installation

pip install mcp-amadeus

💻 Usage Examples

🔍 Basic Usage

from mcp_amadeus import AmadeusMCP

# Initialize the MCP agent
mcp = AmadeusMCP()

# Search for flights
response = mcp.search_flights(
    origin="JFK",
    destination="LHR",
    departure_date="2025-06-15",
    adults=1,
    children=1
)

print(response)

📄 Output Format

[
  {
    "airline": "AA",
    "departure_time": "2025-06-15T10:00:00",
    "arrival_time": "2025-06-15T14:30:00",
    "duration": "04:30",
    "price": 500,
    "currency": "USD"
  },
  ...
]

✨ Features

✈️ Flight Offer Search

Retrieve flight options between two locations on specified dates.

"I'm looking for a flight from JFK to LHR on June 15, 2025, with one adult and one child."

• Sort flights by price, departure time, and airline.
• Display flight information (date, time, duration) and price.

🔧 Technical Details

🛠️ Tools

MCP Agent

The MCP agent provides the following interfaces:

• search_flights(origin, destination, departure_date, **options)
• calculate_price(flight_id, passengers)

📋 Parameter Options

📤 Output

Returns flight offers in JSON format obtained from Amadeus, including airline, time, duration, and price information.

📚 Documentation

• Model Context Protocol Python SDK
• Amadeus Python SDK
• Amadeus API Documentation

📄 License

MIT License © 2025 donghyun-chae