
Amadeus Agent
A proof-of-concept MCP server that allows LLM agents to query live flight booking information via Amadeus, including cheapest tickets, destinations, and airline routes.
README
Travel agent
A simple proof-of-concept MCP server for Amadeus enabling LLM-based agents to use Amadeus as a tool. The server provides tools for LLMs to directly query live flight booking information around the world, including:
- Cheapest tickets for a particular journey.
- All destinations from a particular airport.
- All routes for an airline.
What is MCP?
Model Context Protocol (MCP) is a client-server protocol for LLM agents interacting with tools, resources and prompts. You can think of it as a HTTP for agents. A MCP server hosts a bunch of tools that the agent can use to carry out tasks for the user.
What is Amadeus?
Amadeus is a Global distribution system (GDS), essentially a booking and reservation system used by a large amount of travel agents around the world. It allows querying flight and booking information that would only be available directly to travel agencies and other resellers.
Structure
- agent
--- resources <- static data
--- services <- service layer for tool logic
--- tools <- actual tools provided to llm
server.py <- main server endpoint
Installation
This project relies on the Python uv
project manager uv which enables
easy dependency manage and distribution. Once you have uv
installed you can create a virtual environment
with all of the dependencies included to run the project.
uv install
source .venv/bin/activate
Once installed you will need to provide Amadeus-for-develops credentials in a .env
file in the project root.
The Amadeus developer pages shows you how to acquire such a key. Once you have the key and secret, but them in a .env
file like so:
AMADEUS_KEY=<YOUR-KEY>
AMADEUS_SECRET=<YOUR-SECRET>
Running
When the setup is completed you can start the FastMCP server
python server.py
It is then ready to accept requests from an LLM agent.
Connecting to Claude Desktop
Claude Desktop comes with built-in support for interacting with MCP servers. To enable it you need to open Claude Desktop developer panel and edit your claude_desktop_config.json to start the server.
{
"mcpServers": {
"AmadeusServer": {
"command": "<PATH-TO-PROJECT>/.venv/bin/python",
"args": [
"<PATH-TO-PROJECT>/server.py"
]
}
}
}
Then restart Claude Desktop start a new conversation. Before writing select the AmadeusServer from the configuration panel below the text input.
Claude should now discover your tools and use them to solve your tasks.
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.