How to Use the Duffel Flights MCP in Google ADK

Q: How do I connect the Duffel Flights MCP Server to my Google ADK agent?

Run pip install google-adk and configure McpToolset with your Vinkius HTTP server parameters to start the MCP connection. Pass this toolset into your LlmAgent tools array to expose all eight flight booking tools to Gemini.

Q: Can I use Gemini's 1M token context with Duffel Flights?

Absolutely. When listflightoffers returns dozens of complex flight options, Google ADK passes the entire raw payload into Gemini's long-context window, letting the model analyze subtle differences in layovers or baggage fees.

Q: How do I limit which Duffel Flights MCP tools are exposed to Google ADK?

Use the optional tool name filter in McpToolset to restrict access. For example, you can expose listairports to a basic search agent, while reserving createflightorder for an authorized booking agent.

Q: How are Duffel API rate limits handled in this configuration?

You should implement caching for static endpoints like listaircraft and listairlines using Vertex AI or Google Cloud Memorystore. This prevents your agent from hitting Duffel's rate limits during high-traffic booking sessions.

Build high-scale travel agents with Google ADK and Duffel Flights.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duffel Flights MCP to Google ADK

Create your Vinkius account to connect Duffel Flights to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Duffel Flights with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query flight options via Google ADK

The `create_flight_offer_request` tool initiates the search process by sending passenger counts and route details to Duffel's global distribution system. By using Google ADK, your Gemini agent can process massive lists of flight options in its long-context window without slowing down. To display these options, the agent invokes `list_flight_offers` to retrieve the active fare classes and pricing details. This lets you cross-reference flight deals with customer historical data stored in BigQuery before presenting the top choices.

Complete flight bookings with this MCP Server

Registering passenger information is handled by the `create_flight_order` tool, which locks in selected tickets directly with the airline. Your Google ADK agent processes the structured JSON payload, matching user preferences against live seat maps. Paying for the reserved seats happens when the agent calls `pay_for_flight_order` to process the transaction. This workflow runs securely within your Google Cloud infrastructure, keeping financial transactions isolated from public networks.

Map airports and aircraft in Google ADK

Translating city names into official IATA codes is the job of the `list_airports` tool, preventing costly booking errors. Your Gemini agent queries this tool during the initial chat to ensure the passenger actually wants JFK instead of LGA. You can also call `list_airlines` and `list_aircraft` to fetch carrier details and plane models for the itinerary. This lets your Google ADK agent provide deep flight details, like legroom or Wi-Fi availability, directly from the carrier's fleet database.

Setup guide

Set up Duffel Flights MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Duffel Flights tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Duffel Flights_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Duffel Flights tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Duffel. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Duffel Flights now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Duffel Flights MCP in Google ADK

Run `pip install google-adk` and configure `McpToolset` with your Vinkius HTTP server parameters to start the MCP connection. Pass this toolset into your `LlmAgent` tools array to expose all eight flight booking tools to Gemini.

Absolutely. When `list_flight_offers` returns dozens of complex flight options, Google ADK passes the entire raw payload into Gemini's long-context window, letting the model analyze subtle differences in layovers or baggage fees.

Use the optional tool name filter in `McpToolset` to restrict access. For example, you can expose `list_airports` to a basic search agent, while reserving `create_flight_order` for an authorized booking agent.

You should implement caching for static endpoints like `list_aircraft` and `list_airlines` using Vertex AI or Google Cloud Memorystore. This prevents your agent from hitting Duffel's rate limits during high-traffic booking sessions.

Passenger names, passport details, and payment tokens are processed in memory through the Vinkius ephemeral sandbox. Google ADK routes this data directly to Duffel's API through the MCP protocol, ensuring no sensitive travel documents are written to Google Cloud logging or persistent storage.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript