How to Use the Travelport MCP in AutoGen

Q: How do I build a comprehensive booking flow with Travelport using AutoGen?

You can set up multiple agents: one to search (searchflights), another to manage the session (createworkbench), and a final agent to execute the booking (commitworkbench). They talk through the steps until consensus is reached.

Q: Can AutoGen handle multi-stage payments for Travelport?

Yes. The agents can debate payment options, running authorizecard and then potentially using reverseauthorization if a simulated failure occurs. This robust negotiation handles edge cases.

Q: Does this MCP Server provide enough data for AutoGen to build a complete travel plan?

It provides coverage across searches (searchstayscomplete), reservations (retrievehotelreservation), and payment methods, giving the agents everything they need to debate.

Simulate complex travel planning decisions using multiple agents with AutoGen.

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 AutoGen

Create your Vinkius account to connect Travelport to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent itinerary construction.

You can build a debate where one agent searches for the next leg of a flight using `search_next_leg`. Another agent then adds this to the current plan via `add_traveler_to_workbench`, while a third commits it with `commit_workbench`. The agents negotiate the best sequence. This simulates real-world travel planning where multiple stakeholders must agree on one path.

Debate optimal booking paths and pricing.

One agent might check a full price using `price_offer_full`, while another checks the catalog reference rate with `price_offer_reference`. They debate which is better, forcing consensus on the final cost. This complex decision-making process is what AutoGen excels at.

Negotiate secure booking requirements.

A security agent runs `verify_address` and checks payment status using `validate_card`. A planning agent then uses the available data to initiate a reservation via `create_hotel_reservation`. The agents must reach agreement on both safety and logistics before proceeding.

Setup guide

Set up Travelport MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Travelport tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Travelport_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Travelport data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Travelport_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Travelport data")
    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 AutoGen

You can set up multiple agents: one to search (`search_flights`), another to manage the session (`create_workbench`), and a final agent to execute the booking (`commit_workbench`). They talk through the steps until consensus is reached.

Yes. The agents can debate payment options, running `authorize_card` and then potentially using `reverse_authorization` if a simulated failure occurs. This robust negotiation handles edge cases.

The agents challenge each other's assumptions. For example, one agent finds an option via `search_stays_by_location`, but another checks the rules using `get_hotel_rules`. They debate which constraint is most important.

It provides coverage across searches (`search_stays_complete`), reservations (`retrieve_hotel_reservation`), and payment methods, giving the agents everything they need to debate.

The system deals with payment card details. When building multi-agent systems, you must ensure all consensus processes involving `authorize_card` maintain strict security protocols.

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