How to Use the Amadeus MCP in Pydantic AI

Build type-safe travel agents with Pydantic AI and the Amadeus MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amadeus MCP to Pydantic AI

Create your Vinkius account to connect Amadeus 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

Setup Amadeus with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strictly typed travel data for Pydantic AI

Every response from `get_airline_info` or `search_flights` is validated against your Pydantic models. If the API returns junk, your agent catches it immediately. This prevents the common issue of silent data corruption in your agent's memory. Your code treats travel data as a reliable object rather than an unpredictable dictionary.

Validate destination activities in Pydantic AI

When you call `search_activities`, the framework ensures the output matches your expected schema. You get a clean list of events that your agent can safely act upon. The runtime validation runs at the tool execution layer. If a field is missing or the type is wrong, the agent throws an error before it can hallucinate a plan.

Secure hotel search for Pydantic AI agents

Use `search_hotels` with full confidence that the pricing and availability data are correctly typed. Your agent works with structured data that is guaranteed to be correct. You maintain total control over your agent's behavior by defining strict models for every tool response. This approach is ideal for production systems where correctness is the priority.

Setup guide

Set up Amadeus MCP in Pydantic AI

Prerequisites

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

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

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

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": {
        "amadeus-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

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 Amadeus. 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 Amadeus 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 Amadeus MCP in Pydantic AI

You use the MCPToolset class to connect to the server. Your agent then maps the tools to your typed functions for full schema validation.

Because it uses Pydantic models, any unexpected data format causes a validation error. This forces your agent to handle the failure instead of failing silently.

Yes, the framework is model-agnostic. Whether you use a local model or a cloud-based one, the tool responses are validated against your types.

Vinkius provides a secure endpoint token for your server. This ensures that only your authorized agent can interact with the Amadeus tools.

It shares flight, hotel, and activity details. We protect your account by isolating this data in a secure sandbox, preventing unauthorized access to your travel credentials.

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