How to Use the WMATA MCP in Pydantic AI

Q: What is the process for checking current Metrorail delays with WMATA and Pydantic AI?

Use getrailincidents. This tool returns structured data on incidents, specifying affected station codes, line impacts, and incident types. You get reliable service disruption awareness.

Q: How can I track bus arrival predictions using WMATA and Pydantic AI?

The getcircuitpredictions tool returns predicted arrival times in minutes for Metrobus Circuit routes. It's designed for accurate, real-time connection coordination.

Q: Does the MCP Server handle accessibility data from WMATA and Pydantic AI?

Yes. getelevatorincidents gives you structured records of outages at Metrorail stations. This includes affected station codes, outage descriptions, and estimated repair times.

Q: If I need to know the total stops on a route, what data type does this MCP Server provide?

The getbusroutedetails tool provides all stops served by the route in order. This structured list ensures your agent has the full service coverage path.

Q: If I need to plan a park-and-ride journey, what data type does this MCP Server provide?

The getparkinglots tool provides parking lot information for specific station codes. You get details on availability and location suitable for planning commuter journeys.

Validated WMATA transit data for your Pydantic AI agent.

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 Pydantic AI

Create your Vinkius account to connect WMATA to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Bus Movements with MCP Server

The `get_bus_positions` tool gives you a structured list of bus vehicle IDs, route IDs, and exact latitude/longitude coordinates. Every data point is validated against these fields. This ensures that when your agent says 'the X2 bus is here,' it's using accurate, type-safe location data.

Get Reliable Incident Status via Pydantic AI

`get_rail_incidents` provides structured incident records for Metrorail—including line impacts, incident types (like 'power problem'), and estimated resolution times. This prevents hallucinations about service status. It ensures that when you check reliability before a journey, the data is correct and verifiable.

Discover WMATA station details with MCP Server

`get_rail_stations` lists all Metrorail stations. By filtering by line code (e.g., 'BL' for Blue Line), you get a guaranteed list of valid station codes needed for subsequent queries. This foundational data prevents your agent from attempting to query non-existent or invalid network locations.

Setup guide

Set up WMATA MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "wmata-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to WMATA tools.",
)

result = await agent.run("List recent WMATA transactions")
print(result.output)

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 Pydantic AI

Use `get_rail_incidents`. This tool returns structured data on incidents, specifying affected station codes, line impacts, and incident types. You get reliable service disruption awareness.

The `get_circuit_predictions` tool returns predicted arrival times in minutes for Metrobus Circuit routes. It's designed for accurate, real-time connection coordination.

Yes. `get_elevator_incidents` gives you structured records of outages at Metrorail stations. This includes affected station codes, outage descriptions, and estimated repair times.

The `get_bus_route_details` tool provides all stops served by the route in order. This structured list ensures your agent has the full service coverage path.

The `get_parking_lots` tool provides parking lot information for specific station codes. You get details on availability and location suitable for planning commuter journeys.

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