How to Use the WMATA MCP in LangChain

Q: How do I check bus delays for WMATA using LangChain?

Start by calling getbusincidents to pull current disruption data. This gives you incident types, affected routes, and alternative service recommendations immediately.

Q: Can my agent track a specific bus route for WMATA using LangChain?

Yes. Use getbuspositions. You feed the desired route ID into this tool, and it returns real-time coordinates and schedule deviation for every vehicle on that line.

Q: What kind of station accessibility info can I get for WMATA using LangChain?

You use getelevatorincidents to find out about outages. This tool provides the affected station codes, outage descriptions, and estimated repair times, which is crucial for planning journeys with mobility needs.

Q: Does WMATA support predicting bus arrivals using LangChain?

Absolutely. Use getcircuitpredictions. You can filter by a station code to get predicted arrival times in minutes for the next Metrobus Circuit train, coordinating with Metrorail connections.

Q: What data type does this WMATA server touch regarding incidents?

The getrailincidents tool touches detailed service disruption information. This includes incident descriptions, affected station codes, line impacts, and estimated resolution times for Metrorail.

Build complex reasoning chains with your AI client on WMATA data.

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 LangChain

Create your Vinkius account to connect WMATA to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Managing Bus Disruptions

When users ask if a bus is delayed, start by calling `get_bus_incidents`. This tool returns incident descriptions, affected route IDs, and detour info. Your agent can then use this data to inform the user about alternative service recommendations or closures. Beyond just finding delays, you'll get specific details like accident types, road closure locations, and start times for any disruption affecting Metrobus service.

Tracking Trains and Buses in Real-Time

Need to know where the next bus is? Use `get_bus_positions` to get real-time coordinates and schedule deviation for all buses. You can filter these results by route ID, making it simple for your agent to answer 'where is the X2 bus.' For rail service, start with `get_rail_stations` to find station codes, then run `get_station_prediction`. This gives you the next train's destination and predicted arrival time right at a specific WMATA station.

Planning Full Journeys from Start to Finish

Route planning is multi-step. First, call `get_bus_routes` to list all possible routes in the system. Then, use `get_bus_route_details` with a specific route ID to map out every single stop it serves in order. To cover the whole journey, you can chain this up. You might check parking availability using `get_parking_lots`, then get entrance details via `get_station_entrances`. This helps your agent build a complete trip itinerary.

Setup guide

Set up WMATA MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes WMATA tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "wmata-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent WMATA transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Start by calling `get_bus_incidents` to pull current disruption data. This gives you incident types, affected routes, and alternative service recommendations immediately.

Yes. Use `get_bus_positions`. You feed the desired route ID into this tool, and it returns real-time coordinates and schedule deviation for every vehicle on that line.

You use `get_elevator_incidents` to find out about outages. This tool provides the affected station codes, outage descriptions, and estimated repair times, which is crucial for planning journeys with mobility needs.

Absolutely. Use `get_circuit_predictions`. You can filter by a station code to get predicted arrival times in minutes for the next Metrobus Circuit train, coordinating with Metrorail connections.

The `get_rail_incidents` tool touches detailed service disruption information. This includes incident descriptions, affected station codes, line impacts, and estimated resolution times for Metrorail.

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