Can my AI track a specific flight in real-time and show me its current position, altitude, and speed?

Yes! Use the `search_flights` tool with the flight number (e.g., "UAL123") to find the active flight, then use `track_flight` with the flight ID to get real-time position coordinates (latitude, longitude), altitude in feet, ground speed in knots, heading direction, and vertical speed. Your AI agent will respond with the exact location of the aircraft and its current flight parameters. Perfect for passenger pickup coordination and live flight monitoring.

How do I find all flights departing from or arriving at a specific airport?

Simply ask the agent to run the `get_airport_flights` action with the airport IATA or ICAO code (e.g., "JFK" or "KJFK" for New York JFK). It will return all arriving and departing flights with airline, flight number, aircraft type, origin/destination, scheduled and actual times, and current status. You can also use `search_airports` first to find the correct airport code if you only know the city name.

Can I look up information about a specific aircraft by its tail number or registration?

Absolutely! Use the `get_aircraft_info` tool with the aircraft registration/tail number (e.g., "N12345" for US, "G-EUUU" for UK, "D-AIMA" for Germany). Your AI will return the aircraft manufacturer and model, registration country, owner/operator, year built, engine type, number of engines, aircraft age, and category (airline, business jet, private, cargo). You can also use `search_aircraft` with an operator name to see their entire fleet.

Netrows MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Netrows
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Netrows 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 Netrows "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Netrows?"
    )
    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 Netrows MCP Server

Connect your Netrows Aviation API flight tracking platform to any AI agent and take full control of real-time flight monitoring, aircraft intelligence, airport operations, and airline schedule analysis through natural conversation.

Pydantic AI validates every Netrows tool response against typed schemas, catching data inconsistencies at build time. Connect 12 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 — Find active and recent flights by flight number, callsign, or origin-destination airport pair
Flight Details — Get comprehensive flight information including airports, times, aircraft, and status
Real-Time Tracking — Monitor live flight positions with coordinates, altitude, speed, and heading
Aircraft Registry — Look up aircraft specifications, ownership, registration, and fleet details
Fleet Analysis — Search all aircraft operated by specific airlines or aviation companies
Airport Intelligence — Query airport static data, codes, locations, and timezone information
Airport Activity — Monitor all arriving and departing flights at any airport worldwide
Airport Search — Find all airports serving a specific city or metropolitan area
Flight Schedules — Access complete flight schedules between any two airports
Airline Monitoring — Track all active flights by airline with real-time operational data
Airline Profiles — Get airline company information including fleet size, hubs, and destinations
Account Usage — Monitor your API credit consumption and remaining quota

The Netrows MCP Server exposes 12 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 Netrows to Pydantic AI via MCP

Follow these steps to integrate the Netrows 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 12 tools from Netrows with type-safe schemas

Why Use Pydantic AI with the Netrows MCP Server

Pydantic AI provides unique advantages when paired with Netrows 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 Netrows integration code

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

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

Netrows + Pydantic AI Use Cases

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

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

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

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

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

Netrows MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Netrows to Pydantic AI via MCP:

get_account_usage

The Netrows API operates on a credit-based system where each API call consumes 1 credit. Essential for monitoring API consumption, budget management, rate limit awareness, and planning integration usage patterns. AI agents should query this when users ask "how many credits do I have left", "what is my API usage this month", or need to monitor their API consumption before running large batch queries. Check your API account usage and remaining credits

get_aircraft_info

g., "N12345" for US-registered, "G-EUUU" for UK). Returns aircraft type (manufacturer and model), registration country, owner/operator information, registration status, year built, engine type (jet, turboprop, piston), number of engines, aircraft age, and category (airline, business jet, private, cargo). Critical for aviation enthusiasts, fleet tracking, aircraft utilization analysis, and private aviation monitoring. AI agents should reference this when users ask "tell me about aircraft N12345", "who owns this tail number", or need aircraft specifications to contextualize flight data. Get registration details and specifications for a specific aircraft

get_airline_flights

g., "UA" for United, "DL" for Delta, "BA" for British Airways). Returns flight numbers, aircraft registrations and types, origin-destination pairs, scheduled and actual times, and current status for all flights in the airline fleet. Essential for airline operations monitoring, fleet utilization analysis, competitor intelligence, and passenger rebooking during disruptions. AI agents use this when users ask "show me all United flights right now", "what is Delta flying", or need to track an entire airline operational picture in real-time. List all active flights operated by a specific airline

get_airline_info

Returns airline name, IATA/ICAO codes, callsign, country of registration, fleet size, destination count, hub airports, and operational status. Essential for airline industry research, competitor analysis, travel planning context, and aviation market intelligence. AI agents should reference this when users ask "tell me about United Airlines", "what is the ICAO code for Delta", or need airline metadata to contextualize flight and fleet data. Get information and details for a specific airline

get_airport_flights

Returns a comprehensive list of inbound and outbound flights with airline/operator, flight number, aircraft type, origin/destination airports, scheduled and actual times, and current flight status (en-route, landed, scheduled, delayed, cancelled, diverted). Essential for airport operations management, passenger pickup coordination, ground handling planning, and flight activity monitoring. AI agents should reference this when users ask "what flights are at X airport", "show me all activity at Y", or need to monitor airport traffic patterns. List all arriving and departing flights at a specific airport

get_airport_info

g., "JFK" or "KJFK" for New York JFK, "LAX" or "KLAX" for Los Angeles International). Returns airport name, location (city, state, country), IATA/ICAO/FAA codes, geographic coordinates (latitude, longitude, elevation), timezone, and operational status. Essential for airport identification, travel planning, flight briefing preparation, and geographic reference. AI agents should use this when users ask "tell me about airport X", "what is the ICAO code for Y", or need airport metadata to contextualize flight queries. Get static information and details for a specific airport

get_flight_details

Returns departure and arrival airports with full metadata (IATA/ICAO codes, terminal, gate), scheduled and actual times for departure and arrival, aircraft registration and type, airline/operator details, current flight status, and tracking coordinates if airborne. Critical for passenger travel updates, airline operations coordination, and flight tracking dashboards. AI agents should reference this when users request detailed status for a known flight, including gate assignments, timing comparisons, and aircraft information. Get complete details for a specific flight

get_flight_schedule

Returns all scheduled flights with airline/operator, flight numbers, aircraft types, departure and arrival times, frequency of service, and days of operation. Essential for route planning, travel itinerary preparation, schedule analysis, and aviation market research. AI agents should reference this when users ask "what flights fly from JFK to LAX", "show me the schedule between ORD and DFW", or need to plan travel between specific airport pairs with comprehensive scheduling options. Get scheduled flights between two airports

search_aircraft

Returns all registered aircraft in the operator fleet with registration numbers, aircraft types (manufacturer and model), ages, and current operational status. Essential for fleet analysis, aviation industry research, competitor intelligence, and operator profile generation. AI agents use this when users ask "show me all United Airlines aircraft", "what planes does Delta operate", or need to analyze fleet composition for a specific aviation operator. Search for all aircraft operated by a specific airline or company

search_airports

Returns all airports (major international, regional, and general aviation) associated with the queried city including IATA/ICAO codes, full names, locations, distances from city center, and airport types. Essential for travel planning, multi-airport city analysis, alternate airport identification, and geographic aviation research. AI agents use this when users ask "what airports serve Chicago", "find airports in London", or need to identify all airports in a metropolitan area for comprehensive flight searches. Search for airports by city name or location

search_flights

The query can be a flight number (e.g., "UAL123"), callsign, or origin-destination airport pair. Returns complete flight identification, airline/operator, aircraft type, departure and arrival airports with IATA/ICAO codes, scheduled and actual times, current position coordinates (latitude, longitude), altitude in feet, ground speed in knots, heading, and flight status (en-route, landed, diverted, cancelled). Essential for real-time flight tracking, passenger pickup coordination, logistics planning, and aviation operations monitoring. AI agents should use this when users ask "where is flight X", "what flights are flying from A to B", or need to track specific flights by number or route. Search for active and recent flights by flight number, callsign, or route

track_flight

Returns timestamped position data that can be used to visualize flight progress on maps, estimate arrival times, and monitor flight trajectory. Essential for live flight tracking applications, passenger monitoring, operations dashboards, and aviation enthusiast displays. AI agents use this when users ask "track this flight live", "where is this aircraft right now", or need continuous position updates for an airborne flight. Track real-time position and status of a specific flight

Example Prompts for Netrows in Pydantic AI

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

"Search for all active United Airlines flights from Newark to San Francisco."

"Show me all airports that serve the city of London and their current flight activity."

"Tell me about aircraft N12345 — who owns it, what type is it, and what flights has it been operating?"

Troubleshooting Netrows MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Netrows + Pydantic AI FAQ

Common questions about integrating Netrows 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 Netrows MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.