How to Use the Duffel MCP in LangChain

Build travel reasoning pipelines in LangChain by chaining live flight and stay data directly into your agent's decision logic.

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 LangChain

Create your Vinkius account to connect Duffel 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 Duffel with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain flight and stay logic

Your agent uses `create_offer_request` to fetch options and immediately passes the output to `list_offers` for selection. This creates a tight loop where the agent evaluates specific travel itineraries without manual intervention. Each step is visible in your trace logs. You see exactly how the agent parses data from `get_airport` or `get_airline` to refine its next move in the chain.

Manage bookings through LangGraph

You can wrap `create_order` and `create_payment` inside a controlled graph structure. This ensures the agent only commits to a booking after it validates the price via `price_offer`. The state management keeps track of your order IDs. If a change is needed, the agent calls `change_order` based on the current state, keeping the entire lifecycle within your LangChain pipeline.

Verify travel metadata

Use this MCP Server to pull aircraft and airport details into your context. The agent queries `get_aircraft` or `list_airports` to verify technical specs before suggesting a route. This data informs the agent's reasoning. By feeding these details into your prompt, you ensure the agent makes decisions based on real-world constraints rather than generic travel logic.

Setup guide

Set up Duffel 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 Duffel 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({
    "duffel-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 Duffel 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 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 LangChain

Install the necessary adapters and initialize the client with your endpoint. Pass the tools retrieved from the server directly into your agent definition.

Yes, by defining a graph that requires intermediate confirmation. You can force the agent to call `price_offer` before it ever touches `create_order`.

The server remains stateless, but you can manage state using LangChain's memory components. Store the order or offer IDs in your session to keep the context active.

You choose exactly which tools to expose when you pass them to your agent. Simply filter the list provided by the server.

All requests for flight and stay information are routed through an encrypted transport layer. We only transmit the specific data required for your selected tool call.

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