mcp-flight-search
Búsqueda de vuelos MCP
Un servicio de búsqueda de vuelos desarrollado con el Protocolo de Contexto de Modelo (MCP). Este servicio demuestra cómo implementar herramientas MCP para la búsqueda de vuelos.
¿Qué es el Protocolo de Contexto Modelo?
El Protocolo de Contexto de Modelo (MCP) es un estándar desarrollado por Anthropic que permite a los modelos de IA usar herramientas mediante la definición de un formato estructurado para sus descripciones, llamadas y respuestas. Este proyecto implementa herramientas MCP que pueden ser utilizadas por Claude y otros modelos compatibles con MCP.
Related MCP server: Google-Flights-MCP-Server
Instalación
# Install from PyPI
pip install mcp-flight-search
# Or install from the project directory (development mode)
pip install -e .Uso
Inicie el servidor MCP:
# Using the command-line entry point
mcp-flight-search --connection_type http
# Or run directly
python main.py --connection_type httpTambién puede especificar un puerto personalizado:
python main.py --connection_type http --port 5000Variables de entorno
Establezca la clave SerpAPI como una variable de entorno:
export SERP_API_KEY="your-api-key-here"Características
Herramientas compatibles con MCP para la función de búsqueda de vuelos
Integración con SerpAPI Google Flights
Soporte para vuelos de ida y vuelta
Registro enriquecido con salida estructurada
Estructura de código modular y mantenible
Herramientas MCP
Este paquete proporciona las siguientes herramientas de Protocolo de Contexto de Modelo:
search_flights_tool: Busca vuelos entre aeropuertos con los siguientes parámetros:origin: Código del aeropuerto de salida (p. ej., ATL, JFK)destination: Código del aeropuerto de llegada (por ejemplo, LAX, ORD)outbound_date: Fecha de salida (AAAA-MM-DD)return_date: Fecha de regreso opcional para viajes de ida y vuelta (AAAA-MM-DD)
server_status: Comprueba si el servidor MCP se está ejecutando
Estructura del proyecto
mcp-flight-search/
├── mcp_flight_search/
│ ├── __init__.py # Package initialization and exports
│ ├── config.py # Configuration variables (API keys)
│ ├── models/
│ │ ├── __init__.py # Models package init
│ │ └── schemas.py # Pydantic models (FlightInfo)
│ ├── services/
│ │ ├── __init__.py # Services package init
│ │ ├── search_service.py # Main flight search logic
│ │ └── serpapi_client.py # SerpAPI client wrapper
│ ├── utils/
│ │ ├── __init__.py # Utils package init
│ │ └── logging.py # Logging configuration
│ └── server.py # MCP server setup and tool registration
├── main.py # Main entry point
├── pyproject.toml # Python packaging configuration
├── LICENSE # MIT License
└── README.md # Project documentationAutor
Para más artículos sobre IA/ML e IA generativa, sígueme en Medium: https://medium.com/@arjun-prabhulal
Licencia
Este proyecto está licenciado bajo la licencia MIT: consulte el archivo de LICENCIA para obtener más detalles.
Available Tools
2 toolssearch_flights_toolSearch flightsARead-only
Search Google Flights for one-way or round-trip flights between two airports.
Inputs: origin (required), destination (required), outbound_date (required), return_date. Returns: result
server_statusServer statusARead-only
Check that the flight search server is running.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools serve entirely distinct purposes: one performs a flight search, the other reports server health. There is no plausible way to confuse them, and the descriptions make the boundary explicit.
Both names are snake_case, but the convention is inconsistent: 'search_flights_tool' uses a redundant '_tool' suffix and a verb_verb_noun shape, while 'server_status' is a plain noun phrase. Readable, but the pattern isn't predictable.
Two tools is thin for a flight search server; the health-check tool arguably doesn't earn a slot as a first-class tool. It's a borderline-surface rather than an extreme mismatch.
Flight search is covered, but obvious adjacent operations are absent: airport/location lookup, date-range or fare-calendar search, multi-city itineraries, and filtering/sorting of results. An agent can do the core task but will hit dead ends on common follow-ups.
Maintenance
Related MCP Connectors
Search and compare flight offers through a cache-aware Streamable HTTP MCP server for AI agents.
Flight search MCP server providing search, pagination, and itinerary details for AI assistants.
Geo-based flight search MCP server. Find more flights between any two places on earth
Live flight prices and working booking links for AI agents and travel apps.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA 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.18 npm6MIT
- AlicenseNot gradedqualityNot gradedmaintenanceThis MCP server allows an AI assistants to search for flight information online using Google Flights. It can find flights for specific dates or search through a range of dates to find all options or just the cheapest ones available.27-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables flight searching, booking, and payment processing. It also provides access to resources like user profiles, pricing rules, and company travel policies.MIT
- FlicenseNot gradedqualityDmaintenanceAn interactive travel planning server that integrates flight searching, weather forecasting, and route calculation through external APIs like Amadeus and OpenWeather. It uses the Model Context Protocol to enable AI assistants to autonomously manage travel logistics and discover local services.-