Sign in Book a demo
Back to Tools
Search API Key BYOCPro
Build Your Agent View Documentation
google-flights logo

Google Flights MCP Tools for AI Agents

Let an agent look up airports, search one-way, round-trip, and multi-city flights, and retrieve airlines and booking sites for an itinerary.

Available Tools

6 tools available in this integration

GoogleFlights.GetFlightBookingOptions

Resolve a ``booking_token`` to the airlines and OTAs selling that itinerary.

GoogleFlights.ListBookingOptions

Resolve a ``booking_token`` to the airlines and OTAs selling that itinerary.

GoogleFlights.LookupAirports

Find IATA airport codes for a city, country, or airport name.

GoogleFlights.SearchAirports

Find IATA airport codes for a city, country, or airport name.

GoogleFlights.SearchFlights

Search Google Flights for one-way or round-trip itineraries.

GoogleFlights.SearchMultiCityFlights

Search Google Flights for a multi-city (open-jaw) itinerary.

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find the cheapest nonstop flight from Chicago to San Diego next Friday." Arcade picks the right Google Flights actions without guessing airport codes first.

Up to 100x fewer tokens

Google Flights searches return itinerary options and booking details in one response, so the agent can compare routes and prices without loading separate airport and seller records for every option.

Complete the workflow end to end

Find the airport codes, search one-way or round-trip routes, compare itineraries, resolve booking options, and return where to buy through one toolkit designed around the complete flight-search task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Google Flights

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Google Flights, you can implement some of these policies:

Access when tools are listed for a user
  • Decide which tools an agent is allowed to see at all. A tool that is never listed cannot be called, whoever is asking.
Pre-execution before each tool call
  • Inspect the inputs a call is about to run with, and block it or send it for human approval when they fall outside what the agent should do unsupervised.
Post-execution after the tool returns
  • Redact direct booking URLs and tracking parameters from GoogleFlights.GetFlightBookingOptions results, so an agent cannot send travelers to an unapproved airline or OTA.
  • Strip booking tokens and deep links from GoogleFlights.SearchFlights results before they reach the model, so flight research cannot turn into an unreviewed purchase path.
  • Redact booking tokens and provider links from GoogleFlights.SearchMultiCityFlights results, so an agent can compare open-jaw itineraries without forwarding travelers to external sellers.
  • Deny GoogleFlights.ListBookingOptions results when every returned seller falls outside your approved airline and OTA list, so an agent cannot present an unvetted purchase option.
  • Deny GoogleFlights.SearchAirports results for locations on your restricted-destination list, so an agent cannot use airport codes to plan prohibited travel.

How to use Google Flights with your agent

Connect Google Flights to your MCP client and follow the walkthrough from setup to your first flight search. Use the example prompts to test airport lookup, itinerary search, and booking options.

Your questions, answered

A Google Flights MCP server exposes flight-search capabilities as structured tools that an AI agent can call through the Model Context Protocol. It can look up airport codes, search one-way, round-trip, and multi-city itineraries, and identify the airlines and online travel agencies selling a selected itinerary.

Google Flights does not provide the first-party MCP server used here. Arcade built and hosts this integration, adding the authenticated runtime, MCP and tool APIs, approval and redaction policies, and one consistent way to reach flight search from supported clients.

Arcade agents can find airport codes, search one-way and round-trip flights, search multi-city itineraries, and resolve an itinerary to the airlines and online travel agencies that sell it. The integration is read-only: it does not book or purchase flights.

This integration uses a shared API key or secret configured once, rather than Google OAuth permissions for each user. The agent can access only the Google Flights data that the configured credential and integration permit.

No. Users do not each connect a separate Google Flights account. One shared credential is configured once, brokered by Arcade, and never passed to the model; all calls use that configured access.

Yes. Contextual Access policies can require human approval before a Google Flights call proceeds, redact fields from its response, or hide the integration from an agent. All actions in this integration are read-only, so they do not book, purchase, or change a reservation.

Arcade proxies the API calls and does not persist flight-search content as part of normal tool execution. The shared API key or secret is brokered and stored encrypted at rest, and the model never receives it.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the configured authorization remains valid. If the shared key or secret is revoked, rotated, or can no longer be used, calls stop until the credential is reconnected or updated.

Searches remain subject to any limits imposed by Google Flights and the configured Arcade integration. No toolkit-specific quota is exposed in these actions, so applications should handle upstream rate-limit responses and retry appropriately.

Ready to actually ship your agent?

Connect your agent to Google Flights with a shared API key, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Google Flights Quickstart