- Home
- MCP servers
- Amadeus
Amadeus
- python
1
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"eegrcenem-amadeus-agent": {
"command": "<PATH-TO-PROJECT>/.venv/bin/python",
"args": [
"<PATH-TO-PROJECT>/server.py"
],
"env": {
"AMADEUS_ENV": "test",
"AMADEUS_KEY": "<YOUR-KEY>",
"AMADEUS_SECRET": "<YOUR-SECRET>"
}
}
}
}You can run a portable MCP server that lets LLM agents query live Amadeus flight information. This server exposes tools to find the cheapest tickets, list destinations from an airport, and show all routes for an airline, enabling dynamic travel-assisted conversations and automated task planning.
How to use
Start the server using the runtime command shown in the run configuration. The server is designed to be started from a Python virtual environment and will accept requests from an MCP client. Before you begin, ensure your Amadeus credentials are available as environment variables in a .env file at the project root.
How to install
Prerequisites you need: a Python 3.x installation, and the uv package manager for Python projects.
Install the MCP project dependencies using uv:
uv install
source .venv/bin/activate
Create a .env file in the project root and provide your Amadeus API credentials as shown here:
AMADEUS_ENV="test"
AMADEUS_KEY=<YOUR-KEY>
AMADEUS_SECRET=<YOUR-SECRET>
Additional content
Running the server after installation starts the MCP endpoint and enables tool access for your MCP client.
If you want to connect from Claude Desktop, configure the MCP server in the Claude Desktop configuration with the following structure. This enables Claude to launch the server in the same virtual environment and route its requests through the MCP interface.
{
"mcpServers": {
"AmadeusServer": {
"command": "<PATH-TO-PROJECT>/.venv/bin/python",
"args": [
"<PATH-TO-PROJECT>/server.py"
]
}
}
}
Tools exposed by the server
When you query the MCP client, you can access the following capabilities to work with live flight data:
- Cheapest tickets for a given journey
- All destinations from a specific airport
- All routes for a given airline
Available tools
cheapest_tickets
Returns the cheapest flight tickets for a specified journey, suitable for rapid itinerary planning and budgeting.
destinations_from_airport
Lists all destinations available from a given origin airport to help explore travel options.
airline_routes
Provides all routes operated by a specific airline, enabling route-based planning and comparisons.