Amadeus MCP Server
A Model Context Protocol server that connects to Amadeus API, enabling AI assistants to search flights, analyze prices, find best travel deals, and plan multi-city trips.
README
Amadeus MCP Server
This is a Model Context Protocol (MCP) server that connects to the Amadeus API to provide flight search, booking, and analysis capabilities for AI assistants.
Features
- Flight Search: Find flights between airports with various parameters
- Airport Information: Search for airports by keyword, city, or country
- Price Analysis: Get price metrics for routes to determine if current prices are high or low
- Cheapest Dates: Find the most economical dates to travel
- Flight Details: Get detailed information about specific flight offers
Prompts
The server provides several pre-configured prompts for common travel planning scenarios:
- Analyze Flight Prices (
analyze-flight-prices): Analyze flight prices for a route with insights on pricing trends - Find Best Deals (
find-best-deals): Find the best flight deals for a specific route and date - Plan Multi-City Trip (
plan-multi-city-trip): Plan a complete multi-city itinerary with optimal routing - Find Cheapest Travel Dates (
find-cheapest-travel-dates): Identify the most economical dates to travel
Setup
Prerequisites
- Node.js 16.x or higher
- Amadeus API credentials (Client ID and Secret)
Installation
- Clone the repository:
git clone https://github.com/yourusername/amadeus-mcp-server.git
cd amadeus-mcp-server
- Install dependencies:
npm install
- Create a
.envfile in the root directory with your Amadeus API credentials:
AMADEUS_CLIENT_ID=your_client_id
AMADEUS_CLIENT_SECRET=your_client_secret
Running the Server
Build and start the server:
npm run build
npm start
For development:
npm run dev
Testing and Development
This project uses Jest for testing and Biome for linting and formatting.
Run unit tests:
npx jest
Run tests with watch mode:
npx jest --watch
Run tests with coverage:
npx jest --coverage
Run integration tests (requires Amadeus API credentials):
npm run test:integration
Run linting:
npm run lint
Format code:
npm run format
Integration Testing
The project includes comprehensive integration tests that verify the server's interaction with the real Amadeus API. These tests help ensure that our API clients work correctly with the actual API endpoints and handle responses appropriately.
Requirements for Integration Tests
-
Amadeus API Credentials: Tests require valid Amadeus API credentials in the
.envfile:AMADEUS_CLIENT_ID=your_client_id AMADEUS_CLIENT_SECRET=your_client_secret -
Test Environment: Tests are configured to use the Amadeus Test Environment, not the production API.
Running Integration Tests
npm run test:integration
The integration tests are located in __tests__/integration and validate the following API features:
- Airport Search: Searching for airports by code or keyword
- Flight Search: Finding flights for one-way and round-trip journeys
- Price Analysis: Getting price metrics for specific routes
Best Practices for Integration Testing
-
API Rate Limits: The tests include automatic rate limit handling with exponential backoff to avoid API throttling. When running tests frequently, you may still encounter rate limits.
-
Conditional Testing: Tests are designed to skip automatically if API credentials are missing, allowing the test suite to run without errors in environments without credentials.
-
Test in Isolation: When developing a new feature, you can run specific test files:
npx jest __tests__/integration/flight-search.test.js -
Longer Timeouts: Integration tests use longer timeouts (60 seconds) to accommodate network latency and retries.
-
Mock for CI/CD: For continuous integration pipelines where real API access isn't available, use
__tests__/amadeus-mock.test.jswhich runs without actual API calls.
Integration
To use this MCP server with OpenAI's Assistant API or other compatible AI systems, configure the assistant to connect to this server's endpoint.
Tools
The server provides the following tools:
search-flights
Search for flight offers between two locations.
search-airports
Search for airports by keyword, city name, or IATA code.
flight-price-analysis
Get price metrics for a flight route to determine if current prices are high or low.
get-flight-details
Get detailed information about a specific flight offer.
find-cheapest-dates
Find the cheapest dates to fly for a given route.
Resources
The server provides schema resources for:
- Flight offers (
schema://flight-offers) - Airports (
schema://airports)
License
MIT
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.