How to Use the Travelport MCP in LangChain

Q: How do I check availability and book with Travelport using LangChain?

You start by calling searchstayscomplete to see what's available. Once the agent has options, it can use addoffertoworkbench and then finish the trip by executing commitworkbench.

Q: Can I handle payment failures and retries with Travelport and LangChain?

Absolutely. If a booking fails, your chain can use reverseauthorization to claw back funds, followed by re-validating the card with validatecard. This handles complex failure logic.

Q: Does this MCP Server support retrieving past travel data for LangChain?

Yes. You can retrieve existing reservations using retrieveflightreservation or check hotel details via retrievehotelreservation, giving your agent access to historical context.

Build multi-step travel booking flows with your AI client using LangChain.

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 LangChain

Create your Vinkius account to connect Travelport to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Plan complex searches across flights and hotels.

Your agent uses `search_flights` or `search_stays_complete` to gather initial product data. It's perfect for building chains where the output of a broad search becomes the precise input for another tool call. This structure lets your AI client dynamically decide if it needs to check hotel rules using `get_hotel_rules` or narrow down flight options with `search_flight_specific`. The whole process is visible in LangSmith tracing.

Execute secure, multi-stage booking workflows.

The core workflow starts when your agent calls `create_workbench`, setting up the session. Next, you can add details using `add_traveler_to_workbench` and then attach an offer with `add_offer_to_workbench`. Finally, committing requires calling `commit_workbench`, completing the sequence in one chain.

Validate payment data before final booking.

Before committing anything, the agent must verify credentials. It first runs `validate_card` and then checks the billing address with `verify_address`. If all payments pass these steps, you can confidently proceed to authorize funds using `authorize_card`. This is a critical sequence for any robust MCP Server application.

Setup guide

Set up Travelport MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Travelport tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "travelport-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Travelport transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You start by calling `search_stays_complete` to see what's available. Once the agent has options, it can use `add_offer_to_workbench` and then finish the trip by executing `commit_workbench`.

The system provides two main pricing methods: full product pricing via `price_offer_full`, or catalog reference pricing using `price_offer_reference`. Your agent selects the right one based on the context.

Absolutely. If a booking fails, your chain can use `reverse_authorization` to claw back funds, followed by re-validating the card with `validate_card`. This handles complex failure logic.

Yes. You can retrieve existing reservations using `retrieve_flight_reservation` or check hotel details via `retrieve_hotel_reservation`, giving your agent access to historical context.

The server handles sensitive payment card data, including validation and authorization attempts. This is why secure multi-step processing is so important for compliance.

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