How to Use the Navitia MCP in Pydantic AI

Q: How do I register the Navitia toolset in my Pydantic AI agent?

Use the unified MCPToolset class pointing to your Vinkius server URL. Pass this instance in the toolsets list when initializing your type-safe agent.

Q: How do I fetch a complete station timetable with strict typing?

Call getstopschedule to retrieve full timetables for any transit stop. The framework validates the returned weekday, weekend, and holiday service patterns against your predefined data structures.

Inject type-safe European transit data into Pydantic AI agents with the Navitia MCP Server to guarantee valid routing schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Navitia MCP to Pydantic AI

Create your Vinkius account to connect Navitia 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 Navitia with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Plan validated trips with the Navitia MCP Server

`plan_journey` outputs detailed multimodal itineraries including walking times, transfers, and fare estimates across European transit networks. Your type-safe agent validates these complex schedules against strict schemas before presenting them to users. Pydantic AI intercepts the raw tool output to ensure every coordinate, timestamp, and price matches your expected data models. If the transit API returns an unexpected format, your system catches it immediately.

Retrieve verified arrival boards and platform data

`get_arrivals` returns upcoming arriving services, platform numbers, and real-time delay indicators for passenger coordination. Your agent uses this tool to monitor incoming trains and coordinate tight connections. The framework parses every incoming arrival time and platform string through runtime type checks. This prevents your passenger dashboard from displaying corrupt data or broken timetables.

Inspect transit lines and regional operator metadata

`get_lines` lists active transit lines, network affiliations, transit modes, and route colors for regional networks. Your agent queries this tool to map out the structure of local transit systems. Every line color, code, and operator name is validated against your Pydantic schemas. This guarantees that your UI renders exact hex colors and correct transit mode strings without crashing.

Setup guide

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

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

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

Use the unified `MCPToolset` class pointing to your Vinkius server URL. Pass this instance in the toolsets list when initializing your type-safe agent.

Pydantic AI will instantly raise a validation error at runtime rather than letting corrupt data slip through. This guarantees your agent never processes hallucinated schedules or malformed coordinates.

Yes, this framework is completely model-agnostic. You can bind the transit tools to local models or commercial APIs while maintaining strict schema validation.

Call `get_stop_schedule` to retrieve full timetables for any transit stop. The framework validates the returned weekday, weekend, and holiday service patterns against your predefined data structures.

All transit search terms and stop IDs pass through an ephemeral, zero-trust V8 sandbox. Vinkius handles the authorization token securely, ensuring your raw routing queries are never written to persistent storage.

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