How to Use the Duffel MCP in AutoGen

Enable multi-agent debate for travel planning using the Duffel MCP Server to negotiate flight and stay bookings.

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 AutoGen

Create your Vinkius account to connect Duffel 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 Duffel with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate travel itineraries

One agent proposes a flight using `create_offer_request` while another checks the budget using `price_offer`. They debate the trade-offs before settling on a final selection. This prevents hasty decisions. The agents challenge each other on price and timing until they reach a consensus that satisfies your constraints.

Negotiate booking modifications

If a flight is cancelled, your agents use `cancel_order` and `change_order` to discuss the best alternative. They analyze the impact of each change before executing. You get a deliberated solution. The agents weigh the cost of changes against your preferences, ensuring the final choice is intentional and calculated.

Coordinate stay selections

Agents use `list_accommodation` and `quote_stay` to compare lodging options. They verify availability and rates before the final agent creates the booking. The conversation history shows their reasoning. You see exactly why they chose a specific property based on the data pulled from the server.

Setup guide

Set up Duffel 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 Duffel 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="Duffel_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Duffel 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="Duffel_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Duffel 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 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 AutoGen

Install the required extensions and pass the tool list from the MCP Server to your AssistantAgent. The adapter handles the schema conversion automatically.

Yes, you can define agents with different roles, such as a budget-focused agent and a schedule-focused agent, to debate the offer selection.

You can combine this server with others in your agent configuration. The agents can then use tools from multiple sources to make a decision.

Review the chat history between agents. Every call to a tool like `create_order` is logged as part of their conversation.

The server uses a single endpoint token for authentication. Your sensitive credentials and booking info never leave the secure, isolated environment of your agent's execution.

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