How to Use the Netrows MCP in OpenAI Agents SDK

Q: How does my OpenAI Agent use Netrows to find all flights from JFK to LAX?

Your agent will use the getflightschedule tool from the Netrows MCP server. It passes 'JFK' and 'LAX' as parameters and gets back a list of all scheduled flights, including times and flight numbers.

Q: What's the best way to track a flight in real-time with Netrows and an OpenAI Agent?

The agent should first find the flight using searchflights. Then, it calls the trackflight tool with the flight ID. This provides a continuous stream of position data your agent can process.

Q: How do I prevent my OpenAI agent from running out of Netrows API credits?

Have your agent periodically call the getaccountusage tool. This reports your remaining credits, so the agent can decide whether to run a large batch of queries or notify you first.

Build production aviation agents with the OpenAI Agents SDK and real-time Netrows flight data.

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 OpenAI Agents SDK

Create your Vinkius account to connect Netrows to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Safe, Autonomous Flight Tracking

Your agent can now manage its own API budget. Before running a big job, like pulling schedules with `get_flight_schedule` for multiple routes, the agent first checks its credit balance using `get_account_usage`. This built-in guardrail prevents accidental overages. Then, you can create specialized agents that hand off tasks. One agent might use `search_airports` to find all airports in a region, passing the list to another agent that queries `get_airport_flights` for each one. OpenAI's tracing dashboard lets you see every step.

Get Granular Aircraft and Airline Intel

Go beyond simple flight tracking. Your agent can pull detailed specs for any aircraft using its tail number with `get_aircraft_info`, giving you the model, owner, and age. It's perfect for building a fleet analysis tool. You can also get a complete operational picture for any airline. Just ask your agent to use `get_airline_flights` to see every active flight for a carrier, or use `get_airline_info` to get their fleet size and hub airports.

Your OpenAI Agent Is Now a Flight Operations MCP Server

Give your agent the tools to answer almost any aviation question. It can find specific flights with `search_flights` using just a flight number or route. Once found, it can get gate and terminal details with `get_flight_details`. For live tracking, your agent just needs to call `track_flight`. This gives it a stream of real-time coordinates, altitude, and speed. Your agent can use this data to update a map or provide continuous status updates. This MCP server handles the connection.

Setup guide

Set up Netrows MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Netrows tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Netrows tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Netrows tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Netrows Agent",
            instructions="You have access to Netrows tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent will use the `get_flight_schedule` tool from the Netrows MCP server. It passes 'JFK' and 'LAX' as parameters and gets back a list of all scheduled flights, including times and flight numbers.

Yes. While the agent auto-discovers all tools, you can configure guardrails and permissions within the OpenAI Agents framework to restrict access to specific Netrows tools you don't want it to use.

The agent should first find the flight using `search_flights`. Then, it calls the `track_flight` tool with the flight ID. This provides a continuous stream of position data your agent can process.

Have your agent periodically call the `get_account_usage` tool. This reports your remaining credits, so the agent can decide whether to run a large batch of queries or notify you first.

Yes. Your queries for flight numbers, aircraft registrations, and airport codes are sent over an encrypted connection to the Netrows MCP server. Vinkius processes the request ephemerally and doesn't store your specific search 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