How to Use the Travelport MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle large-scale Travelport bookings?

The agent uses structured tools like createworkbench and subsequent data additions to build a reservation. The built-in guardrails validate every action, ensuring that your booking process adheres strictly to operational rules before it runs.

Q: If I need to check hotel rules with Travelport using OpenAI Agents SDK, what tool do I use?

You should call gethotelrules. This function pulls the specific operational guidelines for a given hotel property. It ensures your agent knows exactly what's possible before trying to book anything.

Q: Can the OpenAI Agents SDK validate payment details when booking with Travelport?

Yep, it can. Your agent runs validatecard and verifyaddress. This confirms that the card is active and the billing address matches the bank's records before attempting a final transaction.

Q: If I need to check data privacy for traveler information when using Travelport with OpenAI Agents SDK?

The server touches traveler details. When your agent adds a traveler, it handles identifying information like names and passport numbers. You must ensure these are handled according to client security standards.

Deploy robust travel booking workflows with your AI client and OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Travelport MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Handle complex bookings using the MCP Server.

You can initiate a new session by calling `create_workbench`, which sets up the initial reservation context. After gathering all necessary details, use `add_traveler_to_workbench` and `add_offer_to_workbench` to populate that workbench with air offers or traveler data. The final step is committing the deal. Running `commit_workbench` takes everything in that session and locks it down into a confirmed booking. It’s designed for production reliability, so you can trust these handoffs when deploying your agent.

Search flights across global inventory.

Need to find air options? Start broad with `search_flights` to pull general catalog offerings. If you know more details, narrow it down using `search_flight_specific`. For multi-city trips, you'll use `search_next_leg` to stitch together itinerary components. These searches give your agent the options it needs before pricing them out. You can then run `price_offer_full` or reference a specific catalog item with `price_offer_reference`.

Manage payments and reservations.

The server handles payment processing through several tools. Before booking, your agent needs to validate the card using `validate_card` and verify the billing address via `verify_address`. If things go wrong, you can reverse charges with `reverse_authorization`. Booking confirmation involves both hotel and flight management. Use `create_hotel_reservation` for accommodations or retrieve existing ones with `retrieve_hotel_reservation`.

Setup guide

Set up Travelport 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 Travelport tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Travelport 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="Travelport Agent",
            instructions="You have access to Travelport 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 Travelport. 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 Travelport 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 Travelport MCP in OpenAI Agents SDK

The agent uses structured tools like `create_workbench` and subsequent data additions to build a reservation. The built-in guardrails validate every action, ensuring that your booking process adheres strictly to operational rules before it runs.

The MCP Server manages three core product lines: air travel (using `search_flights`), hotels (via `search_stays_complete`), and the overall booking session itself. The agent treats them as integrated parts of a single trip.

You should call `get_hotel_rules`. This function pulls the specific operational guidelines for a given hotel property. It ensures your agent knows exactly what's possible before trying to book anything.

Yep, it can. Your agent runs `validate_card` and `verify_address`. This confirms that the card is active and the billing address matches the bank's records before attempting a final transaction.

The server touches `traveler` details. When your agent adds a traveler, it handles identifying information like names and passport numbers. You must ensure these are handled according to client security standards.

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