How do I get a Duffel Access Token?

Sign up for a developer account at the [**Duffel Dashboard**](https://app.duffel.com/). You can generate both 'test' tokens for development and 'live' tokens for real bookings.

Can I make real bookings with this agent?

Yes, if you provide a 'live' access token, the agent can perform real flight bookings. We recommend using a 'test' token first to understand the search and booking flow.

Duffel Flights MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Duffel Flights
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Duffel Flights through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Duffel Flights "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Duffel Flights?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Duffel Flights MCP Server

Connect your AI agent to Duffel, the modern infrastructure for travel. This integration allows you to search for real-time flight offers, manage bookings (orders), and access a comprehensive directory of airlines, airports, and aircraft through natural conversation.

Pydantic AI validates every Duffel Flights tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Flight Search — Create offer requests to find the best flights based on origin, destination, dates, and cabin class
Booking Management — Create flight orders (instant or hold) and retrieve detailed reservation information
Payment Processing — Pay for flight orders that were previously held directly via the agent
Travel Directory — List and inspect aircraft models, airlines, and airports worldwide with their respective IATA codes
Order Oversight — List all flight bookings associated with your account to track your travel history

The Duffel Flights MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Duffel Flights to Pydantic AI via MCP

Follow these steps to integrate the Duffel Flights MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 8 tools from Duffel Flights with type-safe schemas

Why Use Pydantic AI with the Duffel Flights MCP Server

Pydantic AI provides unique advantages when paired with Duffel Flights through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Duffel Flights integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Duffel Flights connection logic from agent behavior for testable, maintainable code

Duffel Flights + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Duffel Flights MCP Server delivers measurable value.

Type-safe data pipelines: query Duffel Flights with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Duffel Flights tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Duffel Flights and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Duffel Flights responses and write comprehensive agent tests

Duffel Flights MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Duffel Flights to Pydantic AI via MCP:

create_flight_offer_request

Provide passengers as a JSON array string. Search for flight offers by specifying origin, destination, and passengers

create_flight_order

Provide full passenger details as a JSON string. Book a flight by selecting an offer and providing passenger details

list_aircraft

Retrieve a list of aircraft used by airlines

list_airlines

Retrieve a list of airlines

list_airports

Retrieve a list of airports

list_flight_offers

Retrieve all available flight offers for a specific offer request

list_flight_orders

Retrieve a list of all flight bookings (orders)

pay_for_flight_order

Process payment for a flight order that was previously put on hold

Example Prompts for Duffel Flights in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Duffel Flights immediately.

"Search for a flight from London (LHR) to New York (JFK) on 2024-12-01."

"List all airports in Brazil."

Troubleshooting Duffel Flights MCP Server with Pydantic AI

Common issues when connecting Duffel Flights to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Duffel Flights + Pydantic AI FAQ

Common questions about integrating Duffel Flights MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Duffel Flights MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.