How to Use the WMATA MCP in Mastra AI

Q: How do I handle WMATA circuit predictions with Mastra AI?

The workflow uses getcircuitpredictions to get next bus arrival times. You can build conditional logic: if the predicted time is over 20 minutes, flag it as a significant delay and trigger an alternative service search.

Q: Can Mastra AI confirm elevator status for WMATA stations?

Yes. Use getelevatorincidents to check station accessibility. The workflow can verify if the outage description impacts a specific route, ensuring passengers with mobility needs get accurate information.

Q: What data type does the WMATA MCP Server touch regarding service reliability?

The server tracks both Metrorail and Metrobus reliability. getrailincidents provides line impacts (Metrorail), while getbusincidents details incident types like accidents or road closures for buses.

Q: What is the best way to list all WMATA stations using Mastra AI?

Start by calling getrailstations. This gives you a comprehensive list of station codes and lines. You can then iterate through this list in your workflow to gather details for other services.

Q: Does the WMATA MCP Server provide entrance information needed for Mastra AI?

Yes, use getstationentrances. This tool provides names, addresses, and crucial accessibility info (escalator/elevator) for every entrance at a given station.

Build complex WMATA workflow automations with Mastra AI's durable and retriable MCP Server integrations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WMATA MCP to Mastra AI

Create your Vinkius account to connect WMATA to Mastra AI 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 WMATA with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Trip Planning Workflows

You can build a multi-step flow that first calls `get_bus_routes` to identify service IDs. Next, the workflow uses those IDs in `get_bus_positions` to calculate real-time vehicle locations. If the data fails or is incomplete, Mastra AI retries the call using exponential backoff. This makes complex WMATA journey planning reliable, handling failures gracefully so your application never crashes on a service disruption.

Service Disruption Escalation

Set up a workflow that monitors multiple incident sources. For instance, it checks `get_rail_incidents` for Metrorail delays and simultaneously calls `get_bus_incidents`. If both report major disruptions, the flow automatically flags an admin and notifies via a secondary tool. Mastra AI's conditional branching handles this logic: if one service is fine but the other isn't, it executes specific alternative routing steps.

Park-and-Ride Booking Logic

Develop a system that needs to check commuter parking availability. The workflow starts by calling `get_parking_lots` using a target station code. If spaces are low, the next step triggers an alternative search for nearby feeder bus routes via `get_bus_routes`. This structured approach manages resource constraints and builds robust user paths that account for capacity limits.

Setup guide

Set up WMATA MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All WMATA tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "wmata-mcp-client",
  servers: {
    "wmata-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "WMATA Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to WMATA tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent WMATA transactions"
);
console.log(result.text);

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 WMATA. 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 WMATA 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 WMATA MCP in Mastra AI

The workflow uses `get_circuit_predictions` to get next bus arrival times. You can build conditional logic: if the predicted time is over 20 minutes, flag it as a significant delay and trigger an alternative service search.

Yes. Use `get_elevator_incidents` to check station accessibility. The workflow can verify if the outage description impacts a specific route, ensuring passengers with mobility needs get accurate information.

The server tracks both Metrorail and Metrobus reliability. `get_rail_incidents` provides line impacts (Metrorail), while `get_bus_incidents` details incident types like accidents or road closures for buses.

Start by calling `get_rail_stations`. This gives you a comprehensive list of station codes and lines. You can then iterate through this list in your workflow to gather details for other services.

Yes, use `get_station_entrances`. This tool provides names, addresses, and crucial accessibility info (escalator/elevator) for every entrance at a given station.

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