How to Use the Netrows MCP in Pydantic AI

Q: What's the best way to get airport information with Netrows and Pydantic AI?

Have your agent call the getairportinfo tool with an IATA or ICAO code. Pydantic AI will return a validated object containing the airport's name, location, and coordinates, ready to be used in your Python code.

Q: How do I check my API credit balance using Netrows and Pydantic AI?

Just have your agent call the getaccountusage tool. It takes no parameters and returns a validated Pydantic object with your current credit status, ensuring the data is always structured correctly.

Get type-safe, validated aviation data in your Python app with Pydantic AI and Netrows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Netrows MCP to Pydantic AI

Create your Vinkius account to connect Netrows 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 Netrows with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Eliminate Bad Data with Runtime Validation

Stop worrying about silent API failures. When your agent calls a Netrows tool like `get_flight_details`, Pydantic AI automatically validates the response against a Pydantic model. You get exactly the data structure you expect. If the API ever returns something unexpected—a missing field, a wrong data type—your code will raise a `ValidationError` immediately. No more chasing down bugs caused by corrupted or incomplete flight data.

Build Reliable Aviation Logic with a Pydantic AI MCP Server

Write code that's both readable and correct. You can ask your agent to find a flight with `search_flights` and then pass the validated output directly to another function that calls `get_aircraft_info`. The types are checked at every step. This makes it simple to build reliable chains of logic. For instance, get a schedule with `get_flight_schedule`, then iterate through the flights to get details for each one using `get_flight_details`. The Pydantic models ensure data compatibility between tool calls.

Model-Agnostic Access to Flight Data

Use the LLM that fits your project. Pydantic AI doesn't lock you into a single provider. You can point it at an OpenAI, Anthropic, or local model, and it will still correctly call the Netrows tools. This lets you swap backends without rewriting your core logic. Your agent's ability to `track_flight` or `search_airports` remains consistent, because the MCP server tool definitions are standardized.

Setup guide

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

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

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

When your Pydantic AI agent calls a Netrows tool, the JSON response is immediately parsed and validated against a corresponding Pydantic model. If the data doesn't match the expected schema, it raises an error, preventing bad data from entering your application.

Absolutely. Pydantic AI is model-agnostic. You can configure it to use a local model, and it will still be able to correctly format requests and call tools on the Netrows MCP server.

Have your agent call the `get_airport_info` tool with an IATA or ICAO code. Pydantic AI will return a validated object containing the airport's name, location, and coordinates, ready to be used in your Python code.

Just have your agent call the `get_account_usage` tool. It takes no parameters and returns a validated Pydantic object with your current credit status, ensuring the data is always structured correctly.

Your requests are securely transmitted to the Vinkius platform, which hosts the Netrows server. The server instance handling your query for flight or airport data is isolated and ephemeral; it processes the request and is then destroyed, leaving no trace of your query history.

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