4,500+ servers built on MCP Fusion
Vinkius
Duffel Flights logo
Vinkius
Pydantic AI logo

How to Use the Duffel Flights MCP in Pydantic AI

Build type-safe, validated booking agents with Pydantic AI and Duffel Flights.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Duffel Flights MCP on Cursor AI Code Editor MCP Client Duffel Flights MCP on Claude Desktop App MCP Integration Duffel Flights MCP on OpenAI Agents SDK MCP Compatible Duffel Flights MCP on Visual Studio Code MCP Extension Client Duffel Flights MCP on GitHub Copilot AI Agent MCP Integration Duffel Flights MCP on Google Gemini AI MCP Integration Duffel Flights MCP on Lovable AI Development MCP Client Duffel Flights MCP on Mistral AI Agents MCP Compatible Duffel Flights MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Pydantic AI

Connect Duffel Flights MCP to Pydantic AI

Create your Vinkius account to connect Duffel Flights to Pydantic AI 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

Validate flight searches using Pydantic AI

Generating a structured search query for flights based on origin, destination, and passenger counts is exactly what the `create_flight_offer_request` tool does. Pydantic AI enforces strict typing on this payload at runtime, ensuring your agent never sends malformed date formats or invalid airport codes to the Duffel API. Once the request is sent, the agent calls `list_flight_offers` to parse the returned ticket options. Because Pydantic AI validates every field against your schemas, any unexpected API changes will raise an immediate, catchable validation error instead of corrupting your booking flow.

Execute flight bookings with this MCP Server

The `create_flight_order` tool takes passenger details and selected offer IDs to create a pending booking on the airline's GDS. Your Pydantic AI agent validates the passenger's name, date of birth, and contact info against strict schemas before initiating the API call. Paying for the finalized reservation occurs when the agent calls `pay_for_flight_order` to run the transaction. This guarantees that credit card details or payment tokens are fully validated and formatted correctly before hitting the external billing gateway.

Verify airports and fleets in Pydantic AI

Real-time validation of airport IATA codes and locations during user input is handled by the `list_airports` tool. Pydantic AI uses this tool to check that the user's origin and destination are valid airports before running a flight search. Your agent can also query `list_airlines` and `list_aircraft` to retrieve carrier names and plane configurations. This metadata is parsed into strongly-typed Python models, making it easy to display seat layouts or baggage rules to the user.

Setup guide

Set up Duffel Flights MCP in Pydantic AI

Prerequisites

  • Python 3.10+ installed
  • pydantic-ai-slim[fastmcp] package
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install Pydantic AI with FastMCP

    Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.

  2. 2

    Configure the FastMCPToolset

    Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.

  3. 3

    Create and run your agent

    Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py
from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "duffel-flights-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Duffel Flights tools.",
)

result = await agent.run("List recent Duffel Flights transactions")
print(result.output)

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.

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 Flights MCP in Pydantic AI

Install the library using `pip install "pydantic-ai-slim[mcp]"` and instantiate `MCPToolset` with your Vinkius MCP server URL. Pass this toolset into the `Agent` constructor's `toolsets` parameter to auto-discover the booking endpoints.
Flight booking APIs are notoriously complex, but Pydantic AI guarantees that payloads for tools like `create_flight_order` match the expected schema exactly. If the agent hallucinates a passenger field, the runtime validation catches it instantly and forces a retry.
When `list_flight_offers` returns an offer that expires, your agent can catch the validation or API error. You can write a Pydantic AI dependency that automatically triggers a new `create_flight_offer_request` to fetch active ticket prices.
Yes, Pydantic AI is completely model-agnostic. You can connect your Vinkius-hosted MCP server to local models or alternative APIs, and the runtime schema validation will still protect your booking pipeline from hallucinations.
Sensitive passenger names, passport details, and payment tokens are passed directly to Duffel through the MCP pipeline into Vinkius's secure, zero-trust V8 isolate sandbox. Pydantic AI validates this data purely in-memory, ensuring that no unencrypted personal identifiable information (PII) is written to logs or persistent databases.

Start using the Duffel Flights MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 8 tools

We've already built the connector for Duffel Flights. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.