How to Use the HERE Mobility MCP in OpenAI Agents SDK

Q: How do I connect the HERE Mobility MCP Server to the OpenAI Agents SDK?

Install the openai-agents package via pip. Initialize MCPServerStreamableHttp with your endpoint URL. Pass it into the Agent constructor using the mcpservers parameter.

Q: Does the HERE Mobility MCP Server handle real-time transit delays?

The getschedule tool pulls the latest departure and arrival data directly from the station. If the local transit authority pushes a delay to the feed, your OpenAI agent sees it immediately.

Q: Why use discovertrips instead of multimodal search in OpenAI Agents SDK?

You use discovertrips when the user specifically wants pure public transit options. It restricts the results to buses, trains, and ferries without mixing in scooters or long walking segments.

OpenAI Agents SDK integration for HERE Mobility. Route public transit, mix transport modes, and trace every agent decision in production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HERE Mobility MCP to OpenAI Agents SDK

Create your Vinkius account to connect HERE Mobility 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 HERE Mobility with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multimodal routing agents

The `search_multimodal_trips` tool mixes buses, subways, bikes, and walking into a single itinerary for your OpenAI agent. You get exact time breakdowns for each leg of the journey. Your agent reads the origin and destination coordinates, then maps the entire path across the city. Handoffs work perfectly here. A specialized routing agent maps the path, then passes the trip ID to a secondary agent using `get_route_details` to check transfer wait times. The OpenAI dashboard traces every API call so you know exactly why the agent picked a specific route.

Live schedules with guardrails

The `get_schedule` tool pulls the next arriving trains for a specific station ID directly into your agent. Transit schedules change constantly. It filters by direction, grabbing only the northbound departures when a user needs to head uptown. Built-in guardrails ensure the agent doesn't make up departure times. If `get_stations_by_name` returns multiple "Central Station" results, the agent stops and asks for clarification instead of guessing the wrong city.

Map transit via MCP Server

The `get_nearby_stations` tool scans a custom radius around any GPS coordinate to find viable transit hubs. You need to know what facilities exist at the origin and destination before plotting a commute. Once the agent locks onto a location, it fires `get_station_details` to check for wheelchair access or parking. Connecting this MCP Server to your OpenAI setup takes one `MCPServerStreamableHttp` context manager. The agent auto-discovers all eight endpoints instantly. You just set `cacheToolsList=True` and start routing.

Setup guide

Set up HERE Mobility 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 HERE Mobility tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate HERE Mobility 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="HERE Mobility Agent",
            instructions="You have access to HERE Mobility 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 HERE Mobility. 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 HERE Mobility 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 HERE Mobility MCP in OpenAI Agents SDK

Install the `openai-agents` package via pip. Initialize `MCPServerStreamableHttp` with your endpoint URL. Pass it into the Agent constructor using the `mcp_servers` parameter.

No. The API strictly handles planning and discovery. Your agent can suggest taxi integration via `search_multimodal_trips`, but it cannot execute the actual booking.

The `get_schedule` tool pulls the latest departure and arrival data directly from the station. If the local transit authority pushes a delay to the feed, your OpenAI agent sees it immediately.

You use `discover_trips` when the user specifically wants pure public transit options. It restricts the results to buses, trains, and ferries without mixing in scooters or long walking segments.

The MCP Server processes raw GPS coordinates, timestamps, and station search strings like 'Times Square'. Vinkius isolates this data inside a V8 sandbox with zero-trust architecture. Endpoint tokens are ephemeral, meaning your transit queries disappear the moment the connection drops.

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