How to Use the WMATA MCP in Google ADK

Q: How can I find all stations on a specific line using WMATA and Google ADK?

Use getrailstations. You filter by the line code (like 'RD' for Red Line) to get a comprehensive list of every station that exists on that track.

Q: What data does this MCP Server use regarding WMATA train arrivals?

The getnextrail tool returns destination names, line colors, and predicted arrival times in minutes for the entire Metrorail system. It’s your primary source for real-time rail tracking.

Q: Does this MCP Server help plan journeys with WMATA and Google ADK?

Absolutely. You can combine getbuspositions (live bus location) with getnextrail (train arrival prediction). This lets your agent calculate total travel time between modes.

Q: What information is available about station entrances from WMATA and Google ADK?

The getstationentrances tool provides the street address, entrance names, and coordinates for a specific Metrorail station. This helps with first-time visitor navigation.

Q: If I need to know the list of all operating WMATA bus routes, what data type is provided?

The getbusroutes tool provides route IDs, names, descriptions, and specifies if a service is limited-stop, local, or express.

Enterprise WMATA transit data integration for Google ADK.

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 Google ADK

Create your Vinkius account to connect WMATA to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage all WMATA trip planning with MCP Server

The `get_circuit_predictions` tool predicts next bus arrivals at circuit routes, giving you minutes until arrival and the specific vehicle ID. This is great for connecting Metrorail passengers to buses. Your agent can build multi-modal trips. It figures out when a train leaves, then calculates how long until the connecting Metrobus arrives at the stop.

Get Detailed WMATA Route Information

`get_bus_route_details` provides every stop for a specific route in sequence. You also get headsigns and the full path data, which is crucial for mapping or complex journey planning. Don't just know the stops; understand their order. This structure helps you build reliable service area analysis.

Check Station Accessibility with MCP Server

`get_elevator_incidents` reports current elevator and escalator outages at Metrorail stations. It includes affected station codes, descriptions of the outage, and estimated repair times. This is vital for running accessibility checks before an agent suggests a journey to a user with mobility needs.

Setup guide

Set up WMATA MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with WMATA tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="WMATA_agent",
    model="gemini-2.0-flash",
    instruction="You have access to WMATA tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use `get_rail_stations`. You filter by the line code (like 'RD' for Red Line) to get a comprehensive list of every station that exists on that track.

The `get_next_rail` tool returns destination names, line colors, and predicted arrival times in minutes for the entire Metrorail system. It’s your primary source for real-time rail tracking.

Absolutely. You can combine `get_bus_positions` (live bus location) with `get_next_rail` (train arrival prediction). This lets your agent calculate total travel time between modes.

The `get_station_entrances` tool provides the street address, entrance names, and coordinates for a specific Metrorail station. This helps with first-time visitor navigation.

The `get_bus_routes` tool provides route IDs, names, descriptions, and specifies if a service is limited-stop, local, or express.

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