How to Use the American Airlines MCP in OpenAI Agents SDK

Q: How do I get American Airlines flight status with the OpenAI Agents SDK?

Just give your agent the getflightstatus tool from this MCP server. It will automatically know to ask for the flight number and date. The SDK handles the tool discovery and execution for you.

Q: Can I use the OpenAI Agents SDK to find alternate American Airlines flights?

Yes. Your agent can use the getflightschedule tool to see all available flights on a given day. You can then program the agent's logic to suggest alternatives if a specific flight is full or delayed.

Q: What's the easiest way to connect to this server?

Install openai-agents and use the MCPServerStreamableHttp class with your Vinkius URL. Pass that server instance to your Agent constructor. The tools are discovered automatically, so there's no manual mapping.

Build production American Airlines agents with the OpenAI Agents SDK. Get flight data with built-in validation and full tracing in your dashboard.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect American Airlines MCP to OpenAI Agents SDK

Create your Vinkius account to connect American Airlines 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 American Airlines with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check Flight Schedules

The `get_flight_schedule` tool lets your agent pull American Airlines flight times between any two airports. Your OpenAI agent can find direct flights, compare departure times, and even check what kind of plane is scheduled for the route. Because you're using the OpenAI Agents SDK, every action is traceable in your dashboard. You can see exactly what data the agent requested and received from this MCP Server, making it simple to debug your travel planning logic.

Get Real-Time Flight Status

Use the `get_flight_status` tool to track any American Airlines flight in real time. Your agent just needs the flight number and date to get departure gates, arrival times, and delay information. The SDK's built-in guardrails are perfect for this. You can set constraints to prevent the agent from repeatedly polling the API for the same flight, ensuring your production system behaves correctly.

Find Airport Details with your MCP Server

The `get_airport_info` tool gives your agent specifics about any airport American Airlines serves. It's great for finding terminal maps or checking what lounges are available at a layover spot. With the OpenAI Agents SDK, you can even build specialized agents. One agent could handle flight booking while another uses this tool to find airport amenities, then hand off the results for a complete travel itinerary.

Setup guide

Set up American Airlines 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 American Airlines tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate American Airlines 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="American Airlines Agent",
            instructions="You have access to American Airlines 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 American Airlines. 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 American Airlines 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 American Airlines MCP in OpenAI Agents SDK

Just give your agent the `get_flight_status` tool from this MCP server. It will automatically know to ask for the flight number and date. The SDK handles the tool discovery and execution for you.

Yes. Your agent can use the `get_flight_schedule` tool to see all available flights on a given day. You can then program the agent's logic to suggest alternatives if a specific flight is full or delayed.

The server itself doesn't cache flight data, since it needs to be real-time. However, you should set `cacheToolsList=True` in your SDK setup. This caches the tool definitions, not the flight data, which speeds up agent initialization.

Install `openai-agents` and use the `MCPServerStreamableHttp` class with your Vinkius URL. Pass that server instance to your Agent constructor. The tools are discovered automatically, so there's no manual mapping.

Your requests, which contain flight numbers and dates, are sent through Vinkius's ephemeral, zero-trust infrastructure. The server only processes the specific data needed for the query and doesn't store your personal information.

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