How to Use the MTA MCP in Windsurf

Q: How does Windsurf handle MTA real-time subway feeds?

Cascade uses getsubwayfeed to pull live coordinates and delay statuses directly into your IDE via this MCP Server. It parses the GTFS-RT protocol buffers in the background, so you only see clean JSON.

Q: How do I build an MTA bus tracker in Windsurf?

Instruct Cascade to build one. It uses getbusvehicles and getbuspredictions to map bus positions and calculate arrival times, drafting the code and fetching live data simultaneously.

Q: What is the best way to test MTA API connections in Windsurf?

Run getsystemtime through this MCP Server to verify your endpoint credentials instantly. This tool checks your authentication status and synchronizes local clocks with the transit authority's servers.

Q: How do I find specific stop IDs for bus routes?

Query getbusstops with your target route ID. Cascade extracts the exact MonitoringRef codes you need to feed into other arrival tools.

Get live MTA transit feeds directly inside Windsurf as Cascade chains subway updates and bus coordinates autonomously.

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 Windsurf

Create your Vinkius account to connect MTA to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Subways and Buses in Windsurf

`get_subway_feed` pulls real-time arrival data for specific subway lines directly into your active Windsurf coding workspace. Cascade plans the query, selects the correct feed ID, and extracts the exact arrival times without making you prompt each step. Call `get_bus_predictions` to pinpoint when the next bus hits a specific stop. The autonomous agent coordinates these live feeds to build or debug transit-aware apps on the fly.

Map Stops and Routes Automatically

`get_bus_stops` lists every stop along a specific route to help you build precise transit directories. The autonomous agent queries the route details first, then pulls the stop coordinates, and finally maps the geographic coordinates without needing manual intervention. Finding route patterns is straightforward with `get_bus_routes`. This MCP Server delivers raw structural data on local, limited, and Select Bus Service lines so your agent can map out entire transit networks instantly.

Monitor Commuter Rail and Alerts

`get_lirr_feed` fetches live train positions and track assignments for the Long Island Rail Road. Your agent reads this data to check for delays at Penn Station or Grand Central Madison, letting you build status dashboards without writing API boilerplate. Combine this with `get_metro_north_feed` and `get_service_alerts` to build a complete transit monitoring system. Cascade handles the multi-step execution to keep your transit apps updated with the latest service disruptions.

Setup guide

Set up MTA MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the MTA MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my MTA payment history." If connected, Cascade will call the MTA tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "mta-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Cascade uses `get_subway_feed` to pull live coordinates and delay statuses directly into your IDE via this MCP Server. It parses the GTFS-RT protocol buffers in the background, so you only see clean JSON.

Instruct Cascade to build one. It uses `get_bus_vehicles` and `get_bus_predictions` to map bus positions and calculate arrival times, drafting the code and fetching live data simultaneously.

Run `get_system_time` through this MCP Server to verify your endpoint credentials instantly. This tool checks your authentication status and synchronizes local clocks with the transit authority's servers.

Query `get_bus_stops` with your target route ID. Cascade extracts the exact `MonitoringRef` codes you need to feed into other arrival tools.

No, Vinkius handles your MTA token inside this MCP Server sandbox. Windsurf only interacts with the final transit payloads, keeping your personal API credentials completely hidden from external logs.

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