How to Use the MTA MCP in OpenAI Agents SDK

Build production transit agents with MTA data. Integrate directly into your OpenAI Agents SDK workflow for real-time NYC updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MTA MCP to OpenAI Agents SDK

Create your Vinkius account to connect MTA 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 MTA with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time subway tracking for OpenAI Agents SDK

Feed live train positions into your agent using `get_subway_feed`. This provides the raw data needed to calculate exact arrival times for the 1, 2, or A lines without guessing. Your agent parses these updates to answer specific commuter questions. It turns complex protobuf streams into plain English answers for your users.

Bus arrival predictions at your fingertips

Connect your agent to `get_bus_predictions` to pull live arrival data for any stop in the city. You get the exact wait time and vehicle status instantly. Combine this with `get_bus_stops` to build a routing engine inside your agent. It identifies the correct stop ID and fetches the next arrival in a single pass.

Monitor commuter rail status

Use `get_lirr_feed` and `get_metro_north_feed` to monitor the regional rail lines serving the city. Your agent gets immediate access to track information and delay reports. Check `get_service_alerts` before providing any route advice. This prevents your agent from recommending a line that is currently suspended due to maintenance.

Setup guide

Set up MTA 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 MTA tools at runtime.
3

Create your Agent

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

Run the agent

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

The server fetches data directly from the transit source. Your agent processes the response immediately, meaning the delay is limited only by your own network connection.

Yes. You can wrap the tool calls in your existing validation logic. This ensures the agent only acts on verified arrival data.

Yes. Every tool output consumes tokens in the conversation history. Keep your queries specific to avoid unnecessary data overhead.

It does. The implementation uses standard async patterns compatible with your environment. You can await results without blocking your event loop.

Your queries involve public transit data like stop IDs and route numbers. We do not track or store your user-specific location history.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.