How to Use the MTA MCP in CrewAI

Q: How do I pass the MTA tools to my CrewAI agents?

Pass the endpoint URL directly into the mcps array in your agent definition. CrewAI connects via HTTP and exposes the transit tools automatically. Your agents can start pulling GTFS-RT feeds from the MCP server immediately.

Q: Can I restrict which CrewAI agent accesses the MTA data?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. You can give the subway agent access to getsubwayfeed while restricting the bus agent to getbusvehicles on the MCP server.

Deploy autonomous agent teams to monitor and analyze MTA transit data with CrewAI.

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 CrewAI

Create your Vinkius account to connect MTA to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Multi-Agent Transit Operations

The MTA MCP Server turns your CrewAI setup into a full transit command center. You assign one agent to continuously monitor `get_service_alerts` for disruptions. When a switch fails at DeKalb Avenue, that agent alerts the routing agent. The router then queries `get_bus_routes` and `get_bus_stops` to build a detour. The agents share this context in memory. A third communication agent takes the detour data and drafts an alert for the user. Instead of one script trying to do everything, specialized roles handle the real-time feeds, the static geography, and the final output.

Track Regional Trains with CrewAI

Handing `get_lirr_feed` to a dedicated agent manages massive commuter rail datasets. It filters out the noise and isolates the specific trains heading to Jamaica. Meanwhile, a Metro-North agent runs `get_metro_north_feed` to watch the Hudson line. These agents compare scheduled arrivals against real-time positions. They use `get_system_time` from the MCP server to calculate precise delays down to the second. If a train stops moving between stations, the agent updates the crew's shared state immediately.

Analyze Street-Level Bus Data

Calling `get_bus_vehicles` executes rapid street-level bus tracking. An agent grabs the coordinates of every active bus in Brooklyn. It cross-references those positions with `get_bus_predictions` to see which vehicles are falling behind schedule. You can drill down to a single intersection. The agent fires `get_bus_vehicle_at_stop` to check if a specific bus is actually approaching the curb. If the GPS data looks stale, it runs `get_bus_estimated_arrival` to get the scheduled ETA instead.

Setup guide

Set up MTA MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke MTA tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="MTA Analyst",
    goal="Access and analyze MTA data via MCP.",
    backstory="Expert analyst with direct MTA access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent MTA transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="MTA Analyst",
        goal="Access and analyze MTA data via MCP.",
        backstory="Expert analyst with direct MTA access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent MTA transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the endpoint URL directly into the `mcps` array in your agent definition. CrewAI connects via HTTP and exposes the transit tools automatically. Your agents can start pulling GTFS-RT feeds from the MCP server immediately.

Yes. Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. You can give the subway agent access to `get_subway_feed` while restricting the bus agent to `get_bus_vehicles` on the MCP server.

The tool descriptions tell the agent how the lines are grouped. If a user asks about the A train, the agent reads the schema for `get_subway_feed` and knows to pass feed ID "2".

It will if you let an agent loop indefinitely. You must configure your crew's execution strategy carefully. Set clear completion criteria so the agents stop polling `get_service_alerts` once they find the required information.

The MCP server only handles public transit identifiers like stop IDs, route names, and vehicle coordinates. CrewAI transmits the specific function arguments to the endpoint. The server executes the fetch against the transit authority and returns the payload without storing your session data.

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