How to Use the IATA Developer Portal MCP in Pydantic AI

Q: How do I set up the IATA Developer Portal with Pydantic AI?

Install pydantic-ai-slimmcp and define your toolset using the unified MCPToolset class. Pass the Vinkius URL directly to expose searchaircraft and the other five reference tools to your agent.

Run type-safe aviation lookups in Pydantic AI with strict schema validation for every airport, airline, and aircraft query.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IATA Developer Portal MCP to Pydantic AI

Create your Vinkius account to connect IATA Developer Portal 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 IATA Developer Portal with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Prevent silent failures with runtime type validation

Stop messy API payloads from breaking your production code. Pydantic AI validates every response from `search_airports` and `search_airlines` against strict Python models before your agent even sees them. If the upstream source returns an unexpected field format, the system raises a validation error immediately. You catch bad data at the boundary instead of debugging logical errors downstream.

Build model-agnostic Pydantic AI pipelines with this MCP Server

Run your aviation tasks on any LLM provider without rewriting your tool integrations. By registering `get_city_details` with this MCP Server, you can switch between Anthropic, OpenAI, or local models. The tool schemas translate automatically across different model providers. This keeps your architecture flexible as new, cheaper models become available.

Verify API availability before executing complex queries

Avoid hitting broken endpoints during peak travel hours. Your agent can run `check_api_status` to verify connection health before attempting to execute a batch of `list_iata_countries` calls. This conditional execution pattern saves computational resources. It ensures your agent fails gracefully or retries when the developer portal is down for maintenance.

Setup guide

Set up IATA Developer Portal 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": {
        "iata-developer-portal-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent IATA Developer Portal 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 IATA Developer Portal. 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 IATA Developer Portal 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 IATA Developer Portal MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and define your toolset using the unified `MCPToolset` class. Pass the Vinkius URL directly to expose `search_aircraft` and the other five reference tools to your agent.

The framework will raise a validation error instantly. This prevents the agent from hallucinating or working with corrupt data, ensuring your application remains stable.

Yes, because the tool definitions are converted into standard schemas that any compatible model can interpret. You can run your lookups using Ollama or other local setups.

No, do not use the deprecated class. You should use the unified `MCPToolset` class, which handles the connection to Vinkius over HTTP and SSE transports.

Every request to resolve airport, airline, or country codes passes through this MCP sandbox. No lookup history or API credentials are ever cached or stored on disk, keeping your business intelligence private.

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