How to Use the Duffel MCP in CrewAI

Q: How do I assign specific Duffel MCP tools to different agents in CrewAI?

You use the toolfilter option when defining your agents. For example, give your booking agent access to createorder while limiting your research agent to listoffers.

Q: Can CrewAI agents handle hotel reservations and flights in the same session?

Yes. One agent can search for flights using createofferrequest while another runs searchstays to find nearby hotels, combining the results into a single itinerary.

Q: How does CrewAI handle API errors when a flight sells out during booking?

The agent executing createorder receives a failure response. Because of CrewAI's shared memory, it alerts the research agent to find the next best flight immediately.

Q: How are travel booking records and customer profiles secured in this setup?

All booking records returned by getorder pass through secure, encrypted memory channels inside your local environment. The MCP server acts as a stateless proxy, meaning Vinkius never stores traveler profiles.

Deploy specialized agent teams in CrewAI to research, price, and book travel itineraries autonomously.

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 CrewAI

Create your Vinkius account to connect Duffel to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized booking agents running on CrewAI

`create_offer_request` allows your CrewAI agents to connect to the MCP server and kick off a multi-city flight search based on a raw travel brief. The agent parses the user's intent and structures the API request automatically. A separate analyst agent can then use `list_offers` to compare pricing, layovers, and cabin classes. They work together in a shared memory space to pick the absolute best option.

Automated customer support with this MCP Server

`change_order` initiates ticket modifications when a traveler requests a date change or flight upgrade. Your support agent can pull up the existing reservation details using `get_order` to calculate change fees. This eliminates the need for human operators to navigate clunky GDS terminals. The agent handles the back-and-forth with the carrier API and presents the final quote to the customer.

Airport and aircraft lookup tools

`get_aircraft` retrieves specific details about the plane, such as model number and carrier-specific configurations. Your agent uses this data to advise travelers on cabin comfort and Wi-Fi availability. Combined with `get_airport` and `get_airline`, your CrewAI agents can build rich, contextual itineraries. They don't just book flights; they explain connection times and terminal layouts.

Setup guide

Set up Duffel MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Duffel tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Duffel Analyst",
    goal="Access and analyze Duffel data via MCP.",
    backstory="Expert analyst with direct Duffel access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Duffel transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Duffel Analyst",
        goal="Access and analyze Duffel data via MCP.",
        backstory="Expert analyst with direct Duffel access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Duffel transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You use the `tool_filter` option when defining your agents. For example, give your booking agent access to `create_order` while limiting your research agent to `list_offers`.

Yes. One agent can search for flights using `create_offer_request` while another runs `search_stays` to find nearby hotels, combining the results into a single itinerary.

The agent executing `create_order` receives a failure response. Because of CrewAI's shared memory, it alerts the research agent to find the next best flight immediately.

Yes, you can run the crew in a background worker. They will execute the entire search and booking process based on incoming email or chat triggers.

All booking records returned by `get_order` pass through secure, encrypted memory channels inside your local environment. The MCP server acts as a stateless proxy, meaning Vinkius never stores traveler profiles.

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