How to Use the Duffel MCP in OpenAI Agents SDK

Q: How do I initialize the Duffel MCP Server inside my OpenAI Agents SDK project?

Install openai-agents via pip and configure MCPServerStreamableHttp with your Vinkius URL to expose Duffel's 29 travel tools. Pass the server instance directly into the mcpservers list when initializing your OpenAI Agents SDK Agent object.

Q: How do I handle seat selection with the Duffel toolset in OpenAI Agents SDK?

Have your OpenAI Agents SDK agent call Duffel's getseatmaps to retrieve the aircraft layout. The OpenAI Agents SDK agent can then parse the JSON structure to present seat options to the user before calling Duffel's createorder.

Run autonomous flight and hotel booking agents using the OpenAI Agents SDK connected directly to live Duffel travel inventory.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duffel MCP to OpenAI Agents SDK

Create your Vinkius account to connect Duffel to OpenAI Agents SDK 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 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safely book flights with OpenAI Agents SDK

Your OpenAI Agents SDK constructor accepts the Duffel MCP Server endpoint directly to let agents execute `create_offer_request` and `create_order`. Because this Duffel MCP Server exposes live airline inventory, your OpenAI Agents SDK python code handles the entire booking lifecycle using `MCPServerStreamableHttp`. By passing the Duffel toolset to `mcp_servers`, the OpenAI Agents SDK manages complex multi-agent handoffs between search and booking steps. One OpenAI Agents SDK agent finds flights with Duffel's `list_offers` while a supervisor agent checks pricing with `price_offer` before confirming the purchase.

Manage hotel stays and real-time rates

The OpenAI Agents SDK lets your agents search accommodations using Duffel's `search_stays` and pull live pricing with `fetch_stay_rates` inside a unified workflow. It gives your OpenAI Agents SDK agentic workflows the exact tools needed to quote and secure rooms. Your OpenAI Agents SDK system can run Duffel's `quote_stay` to get firm pricing before executing a booking. This Duffel MCP Server maps these tools automatically, allowing your OpenAI Agents SDK agents to handle lodging options alongside flight bookings.

Handle post-booking changes and refunds

When travel plans change, your OpenAI Agents SDK agents can modify or cancel bookings using Duffel's `change_order` or `cancel_order`. This keeps your customer support loops running inside your OpenAI Agents SDK python application without manual support tickets. The OpenAI Agents SDK tracks these Duffel tool calls natively on its tracing dashboard. You see exactly when an OpenAI Agents SDK agent checks a payment using Duffel's `get_payment` or triggers a cancellation, giving you full visibility.

Setup guide

Set up Duffel MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Duffel tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Duffel tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Duffel tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Duffel Agent",
            instructions="You have access to Duffel tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 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 MCP in OpenAI Agents SDK

Install `openai-agents` via pip and configure `MCPServerStreamableHttp` with your Vinkius URL to expose Duffel's 29 travel tools. Pass the server instance directly into the `mcp_servers` list when initializing your OpenAI Agents SDK `Agent` object.

Yes, you can control tool access inside the OpenAI Agents SDK by filtering the exposed Duffel tools list during agent setup. This prevents a Duffel search agent from accidentally calling `create_order` or `create_payment`.

When a Duffel flight offer expires, the server returns an error that your OpenAI Agents SDK agent catches. Your python code can then instruct the OpenAI Agents SDK agent to run Duffel's `create_offer_request` again to fetch fresh inventory.

Have your OpenAI Agents SDK agent call Duffel's `get_seat_maps` to retrieve the aircraft layout. The OpenAI Agents SDK agent can then parse the JSON structure to present seat options to the user before calling Duffel's `create_order`.

Yes, because all passenger names and Duffel flight bookings go through Vinkius's zero-trust V8 sandbox, which isolates every MCP tool execution. No personal travel data is stored on the proxy, ensuring your OpenAI Agents SDK application remains compliant.

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