How to Use the WMATA MCP in AutoGen

Q: How do I check WMATA bus delays using AutoGen?

Run getbusincidents first. The agents can take this input, discussing which routes are most affected and suggesting alternative services to the user.

Q: Can my multi-agent system track a specific bus route for WMATA?

Yes. Use getbuspositions. Your agents pass the desired route ID, receiving real-time coordinates and schedule deviation data for all buses on that line.

Q: What station accessibility info can I verify for WMATA using AutoGen?

The agent uses getelevatorincidents to check the status. This provides affected station codes, outage descriptions, and estimated repair times, letting agents confirm accessibility before advising a journey.

Q: Does WMATA support finding all stations for my system using AutoGen?

Absolutely. Use getrailstations to get the list of all Metrorail stations and their line codes. This foundational data allows other agents to build out detailed trip plans.

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

The getrailincidents tool touches service disruption information, specifically detailing incident descriptions, affected station codes, and estimated resolution times for Metrorail.

Build multi-agent debate systems using WMATA's live data with AutoGen.

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 AutoGen

Create your Vinkius account to connect WMATA to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinating Multi-Modal Trip Planning

When planning a journey, the agents must work together. One agent calls `get_bus_routes` to identify all possible transit options. A second agent then uses `get_station_entrances` with the target station code to find the best street-level approach. This multi-step process—listing routes, finding entrances, and checking bus positions via `get_bus_positions`—allows agents to debate the optimal path for the user.

Determining Service Reliability

To check if a line is running normally, one agent calls `get_rail_incidents`, gathering current delay or power problem reports. A second agent can then cross-reference this with `get_next_train` predictions to provide a final assessment. This negotiation between live incident data and predicted schedules makes the answer reliable.

Finding Specific Route Information

Need details on one specific route? One agent uses `get_bus_route_details` to map out every stop. A second agent might then use `get_circuit_predictions` to predict the arrival time at a few key stops. The agents debate which combination of tools gives the most comprehensive and actionable answer for the user.

Setup guide

Set up WMATA MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes WMATA tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="WMATA_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent WMATA data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="WMATA_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent WMATA data")
    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 AutoGen

Run `get_bus_incidents` first. The agents can take this input, discussing which routes are most affected and suggesting alternative services to the user.

Yes. Use `get_bus_positions`. Your agents pass the desired route ID, receiving real-time coordinates and schedule deviation data for all buses on that line.

The agent uses `get_elevator_incidents` to check the status. This provides affected station codes, outage descriptions, and estimated repair times, letting agents confirm accessibility before advising a journey.

Absolutely. Use `get_rail_stations` to get the list of all Metrorail stations and their line codes. This foundational data allows other agents to build out detailed trip plans.

The `get_rail_incidents` tool touches service disruption information, specifically detailing incident descriptions, affected station codes, 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