Can my AI check when the next subway train is arriving at my station?

Yes! Use the `get_subway_feed` tool with the appropriate feed ID for your line. Feed IDs are grouped: "1" covers lines 1,2,3,4,5,6,S; "2" covers A,C,E; "3" covers B,D,F,M; "4" is G; "5" is J,Z; "6" covers N,Q,R,W; "7" is L; "11" is Staten Island Railway. This returns real-time GTFS-RT data with train positions, trip updates, scheduled vs. real-time arrivals, and delay information. For station-level predictions, combine with `get_stations` to find your station code first.

How do I check when the next MTA bus is arriving at a specific stop?

First use `get_bus_stops` with a route ID to find the stop ID (MonitoringRef) for your location. Then use `get_bus_predictions` with that stop ID to get real-time estimated arrival times, route information, destinations, and delay indicators. For more targeted predictions, use `get_bus_estimated_arrival` which allows filtering by both stop ID and route ID. Stop IDs are numeric identifiers assigned by MTA to each physical bus stop across NYC.

MTA MCP Server for CrewAI 12 tools — connect in under 2 minutes

Name: MTA
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 12 Tools Framework

Connect your CrewAI agents to MTA through the Vinkius — pass the Edge URL in the `mcps` parameter and every MTA tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

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

from crewai import Agent, Task, Crew

agent = Agent(
    role="MTA Specialist",
    goal="Help users interact with MTA effectively",
    backstory=(
        "You are an expert at leveraging MTA tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token — get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in MTA "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 12 available tools "
        "and what they can do."
    ),
)

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

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 MTA MCP Server

Connect your MTA API New York City public transit data platform to any AI agent and take full control of real-time NYC Subway and MTA Bus tracking, arrival predictions, LIRR and Metro-North commuter rail monitoring, and service disruption awareness through natural conversation.

When paired with CrewAI, MTA becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call MTA tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.

What you can do

Subway Real-Time Feeds — Access live GTFS-RT data for all NYC Subway lines with train positions and arrival predictions
Bus Routes — List all MTA bus routes across Manhattan, Brooklyn, Queens, Bronx, and Staten Island
Bus Stops — Get all stops for any bus route with coordinates and sequence information
Bus Predictions — Get real-time estimated arrival times for any bus stop
Bus Vehicle Tracking — Track real-time GPS positions of all active MTA bus vehicles
Service Alerts — Monitor active disruptions across Subway, buses, LIRR, and Metro-North
Subway Stations — List all 472 NYC Subway stations with coordinates, borough, and entrance data
LIRR Tracking — Monitor Long Island Rail Road trains with real-time positions and arrivals
Metro-North Tracking — Track Metro-North Railroad trains serving northern NYC suburbs
Stop-Level Bus Monitoring — Monitor buses at specific stops with targeted arrival predictions
Estimated Arrivals — Get route-filtered arrival estimates for buses at any stop
System Connectivity — Verify API connectivity and synchronize timestamps

The MTA MCP Server exposes 12 tools through the Vinkius. Connect it to CrewAI 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 MTA to CrewAI via MCP

Follow these steps to integrate the MTA MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py — CrewAI auto-discovers 12 tools from MTA

Why Use CrewAI with the MTA MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with MTA through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles — one agent researches, another analyzes, a third generates reports — each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass the Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

MTA + CrewAI Use Cases

Practical scenarios where CrewAI combined with the MTA MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries MTA for raw data, then a second analyst agent cross-references findings and flags anomalies — all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries MTA, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain MTA tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries MTA against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

MTA MCP Tools for CrewAI (12)

These 12 tools become available when you connect MTA to CrewAI via MCP:

get_bus_estimated_arrival

Returns predicted arrival times, route information, destinations, wait times, and delay indicators for each expected bus. Supports both multi-route stop queries and single-route filtered queries. Essential for targeted arrival predictions, route-specific wait time estimation, and passenger trip timing. AI agents should reference this when users ask "when is the next M15 at this stop", "show arrival estimates for route B46 at stop 12345", or need route-filtered arrival data at a specific bus stop. Get estimated arrival times for buses at a stop, optionally filtered by route

get_bus_predictions

Returns predicted arrival times, route IDs, destination information, expected wait times, and whether buses are on schedule or delayed. Based on real-time vehicle tracking and schedule adherence. Essential for real-time bus arrival awareness, passenger waiting time estimation, trip timing, and connection coordination. AI agents should reference this when users ask "when is the next M15 bus at stop 12345", "show predictions for this stop", or need real-time arrival data for a specific bus stop. Stop IDs can be found using get_bus_stops. Get next bus arrival predictions for a specific bus stop

get_bus_routes

Returns route IDs, route names, operators (MTA New York City Bus, MTA Bus Company, private operators under MTA contract), and service area information. Covers local, limited-stop, and Select Bus Service (SBS) routes. Essential for route discovery, service area analysis, transit network understanding, and identifying route IDs for use in stop and prediction queries. AI agents should reference this when users ask "list all bus routes in Manhattan", "what routes serve Brooklyn", or need to identify route IDs for subsequent MTA Bus Time queries. List all MTA bus routes in New York City

get_bus_stops

Returns stop IDs (MonitoringRef), stop names, geographic coordinates (latitude, longitude), stop sequence order, and direction information. Essential for stop discovery, journey planning, accessibility mapping, and identifying stop IDs for use in arrival prediction queries. AI agents should use this when users ask "list all stops on the M15", "find bus stops along Broadway", or need to identify stop IDs for use in get_bus_predictions queries. List all stops for a specific MTA bus route

get_bus_vehicle_at_stop

Returns vehicle IDs, route IDs, current positions, expected arrival times, distances from stop, and operational status. More targeted than system-wide vehicle queries. Essential for stop-level bus tracking, passenger waiting awareness, and real-time arrival estimation at specific stops. AI agents should use this when users ask "what buses are coming to this stop", "track vehicles approaching stop 12345", or need stop-specific bus position data for passenger information. Get buses currently at or approaching a specific bus stop

get_bus_vehicles

Returns vehicle IDs, route affiliations, latitude/longitude coordinates, heading direction, speed, recorded time, and prediction availability. Covers all MTA New York City Bus and MTA Bus Company vehicles in active service. Essential for real-time bus fleet monitoring, passenger arrival estimation, route-level service awareness, and transit operations management. AI agents should use this when users ask "where are all the buses right now", "track bus positions system-wide", or need real-time vehicle position data for fleet visualization. Get real-time positions of all active MTA bus vehicles

get_lirr_feed

Returns train positions, trip updates, scheduled vs. real-time arrivals at stations, delays, track information, and service disruptions across all LIRR branches including Babylon, Ronkonkoma, Hempstead, Port Jefferson, Montauk, and more. Essential for commuter rail tracking, arrival predictions at Penn Station and Grand Central Madison, and LIRR service monitoring. AI agents should reference this when users ask "when is the next LIRR train to Penn Station", "track LIRR train positions", or need real-time commuter rail data for trip planning from Long Island into NYC. Get real-time LIRR train data from the Long Island Rail Road

get_metro_north_feed

Returns train positions, trip updates, scheduled vs. real-time arrivals, delays, track information, and service disruptions across all Metro-North lines including Hudson, Harlem, New Haven, Port Jervis, Pascack Valley, and more. Essential for commuter rail tracking, arrival predictions at Grand Central Madison, and Metro-North service monitoring. AI agents should use this when users ask "when is the next Metro-North train from White Plains", "track Metro-North positions", or need real-time commuter rail data for trip planning from Westchester, Connecticut, or the Hudson Valley into NYC. Get real-time Metro-North Railroad train data

get_service_alerts

Returns alert descriptions, affected lines and stations, severity levels, cause types (maintenance, incident, weather, special events, construction), start and end timestamps, and alternative service recommendations. Essential for service disruption awareness, alternative route planning, passenger communication, and understanding system reliability. AI agents should use this when users ask "are there any delays on the 4/5/6 line", "is LIRR running normally", or need to check service reliability before planning MTA journeys. Get current service alerts and disruptions across the MTA system

get_stations

Returns station IDs, station names, complex IDs (for multi-line stations), borough information (Manhattan, Brooklyn, Queens, Bronx, Staten Island), structure types (underground, elevated, embankment, open cut), latitude/longitude coordinates, and North/East/South/West entrance coordinates. Essential for station discovery, rail network mapping, route planning, and identifying station codes for use in journey planning queries. AI agents should use this when users ask "list all stations in Manhattan", "what is the station code for Times Square", or need to understand the NYC Subway network geography. List all NYC Subway stations with details

get_subway_feed

Supports feed IDs grouped by line: "1" (lines 1,2,3,4,5,6,S), "2" (lines A,C,E), "3" (lines B,D,F,M), "4" (lines G), "5" (lines J,Z), "6" (lines N,Q,R,W), "7" (lines L), "11" (Staten Island Railway), "16" (Shuttle 42nd St), "21" (Shuttle Franklin Ave), "26" (Shuttle Rockaway Park). Returns train positions, trip updates, scheduled vs. real-time arrivals, delays, and service disruptions. Essential for real-time subway tracking, arrival predictions, and service monitoring across the entire NYC Subway system. AI agents should use this when users ask "when is the next 1 train", "show real-time positions for the A line", or need live subway data for trip planning. Feed IDs are required and can be found in MTA documentation. Get real-time subway feed data for specific NYC Subway lines

get_system_time

Returns the official server timestamp in ISO 8601 format. Useful for synchronizing local clocks with the MTA system, verifying API connectivity, testing authentication, and timestamp alignment for real-time data correlation. AI agents should use this as a connectivity check before making more complex queries, or when users need to verify API responsiveness and authentication validity. Get the current MTA Bus Time system timestamp

Example Prompts for MTA in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with MTA immediately.

"Show me the next trains on the 1/2/3 line."

"When is the next M15 bus arriving at the stop near 14th Street and 3rd Avenue?"

"Check if there are any service alerts affecting the LIRR right now."

Troubleshooting MTA MCP Server with CrewAI

Common issues when connecting MTA to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts — check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

The Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

MTA + CrewAI FAQ

Common questions about integrating MTA MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily — when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.