How to Use the Aviationstack MCP in Pydantic AI

Q: How do I add the Aviationstack tools to my Pydantic AI agent?

After installing with pip install "pydantic-ai-slimmcp", create an MCPToolset instance with your Vinkius server URL. Then, pass it in the toolsets list when you initialize your Agent. That's it.

Q: Can I use a local LLM with Aviationstack and Pydantic AI?

Yes. Pydantic AI is model-agnostic. The MCPToolset for Aviationstack is configured separately from your LLM, so you can pair this data source with any supported local or remote model.

Q: What happens if the Aviationstack API changes unexpectedly when I'm using Pydantic AI?

Your agent will raise a ValidationError the moment it receives data that doesn't conform to the expected schema. This prevents malformed data from getting into your application logic, making your system much more predictable.

Get type-safe, validated aviation data in your Python app. Build reliable agents with Pydantic AI and any LLM you want.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aviationstack MCP to Pydantic AI

Create your Vinkius account to connect Aviationstack 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 Aviationstack with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarantee Data Correctness with Pydantic

Stop writing defensive code to handle bad API responses. When your agent calls a tool like `list_flights`, Pydantic AI automatically validates the incoming data against a Pydantic model. If a flight number is missing or a timestamp is malformed, your code will raise a `ValidationError` immediately. This means you can trust the data structures your agent works with. You build your application logic around clean, predictable objects representing flights, airports, and airlines. No more silent failures or data corruption from an unexpected API change.

Build Reliable, Model-Agnostic Agents

Pydantic AI doesn't lock you into a specific LLM. You can use OpenAI, Anthropic, Gemini, or even a local model running on your machine. The Aviationstack tools will work exactly the same way with all of them. Your agent can query for airline fleet data using `list_airlines` and `list_airplanes`, and the response is validated before your code ever sees it. This focus on correctness lets you build durable systems that aren't tied to one provider's ecosystem.

A Simple MCP Server for Type-Safe Workflows

This MCP Server exposes the entire Aviationstack API as a set of simple tools. Your Pydantic AI agent can look up airport infrastructure with `list_airports`, check flight paths with `list_routes`, or even get aviation tax info with `list_taxes`. Integration is just a few lines of code. You create an `MCPToolset` with your Vinkius URL and add it to your agent. Pydantic AI handles the tool discovery and runtime validation, so you can focus on what you want to build with the data, not how to get it reliably.

Setup guide

Set up Aviationstack 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": {
        "aviationstack-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Aviationstack 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 Aviationstack. 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 Aviationstack 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 Aviationstack MCP in Pydantic AI

Pydantic AI inspects the schema provided by the MCP server for each tool. It dynamically creates Pydantic models from that schema and uses them to parse and validate the JSON response from every tool call. If the data doesn't match the expected structure or types, it fails instantly.

After installing with `pip install "pydantic-ai-slim[mcp]"`, create an `MCPToolset` instance with your Vinkius server URL. Then, pass it in the `toolsets` list when you initialize your `Agent`. That's it.

Yes. Pydantic AI is model-agnostic. The `MCPToolset` for Aviationstack is configured separately from your LLM, so you can pair this data source with any supported local or remote model.

Your agent will raise a `ValidationError` the moment it receives data that doesn't conform to the expected schema. This prevents malformed data from getting into your application logic, making your system much more predictable.

It only processes the specific aviation data your agent requests, like flight routes or airport details. Vinkius runs every request in an ephemeral sandbox. Your query and the resulting data are isolated and are never persisted after the request completes.

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