How to Use the Travelport MCP in Pydantic AI

Q: If I need to check hotel rules with Travelport using Pydantic AI, what tool do I use?

You call gethotelrules. Because this uses structured validation, you're guaranteed that the returned rule set will fit your expected data model. That means no guesswork.

Q: Can Pydantic AI validate payment details when booking with Travelport?

Absolutely. The agent runs validatecard and verifyaddress. The output of these tools is validated against your schema, meaning you know the card number format and address response are exactly what they should be.

Q: If I need to check data privacy for traveler information when using Travelport with Pydantic AI?

The server touches traveler details. When your agent processes a workbench, the structured nature of the tools means that sensitive data fields are consistently validated and handled according to their defined types.

Build type-safe agents with guaranteed outputs for your AI client and Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Travelport to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage booking sessions reliably using the MCP Server.

The `create_workbench` tool kicks off a new, isolated session. You populate it by calling `add_traveler_to_workbench` and adding specific offers with `add_offer_to_workbench`. When you're ready to book, running `commit_workbench` finalizes the reservation. Pydantic validation ensures that every step—from initial creation to final commitment—produces data that matches your expected Python schema.

Search and price air travel with guaranteed structure.

Use `search_flights` or `search_flight_specific` to find available flight options. Pricing is handled by two distinct tools: `price_offer_full` for comprehensive pricing, or `price_offer_reference` if you know the catalog reference number. This guarantees structured output when quoting costs. The agent can then use `add_offer_to_workbench` with this validated data.

Perform hotel and payment operations safely.

For hotels, your agent can search broadly using `search_stays_complete`. To secure the booking, it uses tools like `authorize_card` or `create_hotel_reservation`. Payments are further protected by `validate_card`, which checks card validity before any transaction is finalized. This rigorous validation prevents silent data corruption across all operations.

Setup guide

Set up Travelport MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "travelport-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Travelport tools.",
)

result = await agent.run("List recent Travelport transactions")
print(result.output)

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 Pydantic AI

The core of the system validates every MCP response against your defined Pydantic models. If Travelport returns unexpected data for, say, `commit_workbench`, the agent fails loudly with a schema error instead of accepting bad data.

The server handles flights (via search and pricing), hotels (using tools like `search_stays_by_location`), and the entire booking session lifecycle. The framework ensures that data moving between these domains remains correct.

You call `get_hotel_rules`. Because this uses structured validation, you're guaranteed that the returned rule set will fit your expected data model. That means no guesswork.

Absolutely. The agent runs `validate_card` and `verify_address`. The output of these tools is validated against your schema, meaning you know the card number format and address response are exactly what they should be.

The server touches `traveler` details. When your agent processes a workbench, the structured nature of the tools means that sensitive data fields are consistently validated and handled according to their defined types.

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