How to Use the MTA MCP in Pydantic AI

Validate MTA transit data with Pydantic AI. Get type-safe subway and bus updates in your Python agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MTA MCP to Pydantic AI

Create your Vinkius account to connect MTA 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 MTA with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe transit queries for Pydantic AI

Define your schema using Pydantic models to validate the output of `get_subway_feed`. If the transit data structure changes, your agent fails safely instead of continuing with bad info. This ensures your routing logic stays reliable. You only work with data that matches your expected types.

Strict arrival time validation

Use `get_bus_estimated_arrival` to fetch data that gets validated at runtime. Your agent rejects any response that misses required fields or contains malformed timestamps. This prevents runtime errors in your trip planning logic. You get clean, typed data every time you call the tool.

System time synchronization

Call `get_system_time` to verify the server state before running your main transit queries. Your agent uses this to align its internal clock with the MTA system time. This avoids off-by-one errors in your prediction calculations. It acts as a standard heartbeat check for your agent.

Setup guide

Set up MTA 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": {
        "mta-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent MTA 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 MTA. 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 MTA 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 MTA MCP in Pydantic AI

The MCP toolset automatically maps the JSON response to your models. Any mismatch triggers a clear validation error immediately.

Yes. Since the MCP server is model-agnostic, you can pair it with any local model. The validation happens on the Python side.

Your Pydantic models will catch the null value. The agent handles it according to the logic you defined in your model schema.

It is efficient. By using typed responses, you avoid the overhead of manual parsing and cleaning of transit data.

No. The server only communicates via the defined MCP protocol. It has no access to your local codebase or files.

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

Mastra AI sdk-typescript

Start using the MTA MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started