How to Use the Navitia MCP in OpenAI Agents SDK

Q: Can I cache the Navitia MCP Server tools inside my OpenAI Agents SDK system?

Yes, set cacheToolsList=True in your server configuration parameters. This prevents the SDK from querying the Vinkius API for the tool schema on every single request. Your agent startup time will drop significantly.

Q: How does the OpenAI Agents SDK handle transit delays during journey planning with Navitia?

Your agent runs planjourney to pull real-time travel itineraries that already factor in active delays. If a route looks risky, the agent can call getdisruptions to verify the cause and suggest an alternative line.

Q: What is the best way to get full timetables for a specific stop?

Use getstopschedule to pull complete weekday, weekend, or holiday timetables. You can control the level of detail by adjusting the depth parameter in your tool call.

Build production-ready transit assistants with OpenAI Agents SDK and the Navitia MCP Server to route users across Europe.

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 OpenAI Agents SDK

Create your Vinkius account to connect Navitia to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route passengers with the Navitia MCP Server

`plan_journey` calculates multimodal transit routes across European cities using live schedules, walking distances, and fare estimates. Your agent queries this endpoint to compare travel times between trains, bikes, and walking routes. The tool feeds raw route options directly into your OpenAI agent context. It handles complex transfers and wheelchair accessibility options automatically without custom routing code.

Track active service disruptions in real time

`get_disruptions` fetches live service alerts, strike notifications, and maintenance schedules directly from regional operators. This tool lets your agent warn users about delays before they book a ticket. You receive raw severity levels and alternative route suggestions directly in the model context. The agent can immediately trigger a handoff to a rerouting specialist when a major delay is detected.

Locate nearby transit stops automatically

`get_nearby_stops` finds stations, platforms, and points of interest near specific geographic coordinates. Your agent uses this tool to identify where a traveler is standing and what transit lines are within walking distance. Combining this with `search_places` resolves messy text queries into exact geographic coordinates. Your production pipeline gets clean location IDs to feed into schedules without manual geocoding.

Setup guide

Set up Navitia MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Navitia tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Navitia tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Navitia tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Navitia Agent",
            instructions="You have access to Navitia tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Use the streamable HTTP client to connect this MCP endpoint directly. Pass the server instance inside the `mcp_servers` list when initializing your agent. The SDK handles tool discovery and exposes the transit endpoints automatically.

Yes, set `cacheToolsList=True` in your server configuration parameters. This prevents the SDK from querying the Vinkius API for the tool schema on every single request. Your agent startup time will drop significantly.

Your agent runs `plan_journey` to pull real-time travel itineraries that already factor in active delays. If a route looks risky, the agent can call `get_disruptions` to verify the cause and suggest an alternative line.

Use `get_stop_schedule` to pull complete weekday, weekend, or holiday timetables. You can control the level of detail by adjusting the depth parameter in your tool call.

Vinkius acts as a zero-trust proxy, passing your coordinates to Navitia without storing persistent logs of your users' exact locations. All API traffic runs in an ephemeral sandbox environment, keeping transit searches private.

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