How to Use the HERE Mobility MCP in Google ADK

Q: How do I configure the HERE Mobility MCP Server with Google ADK?

Install google-adk via pip. Wrap your Vinkius endpoint URL in StreamableHttpServerParameters and pass it to McpToolset. Assign that toolset to your LlmAgent to expose the routing capabilities.

Q: What is the difference between the station search tools in Google ADK?

The getnearbystations tool lets your agent define a custom search radius around a GPS point. The standard getstations tool uses a fixed default radius for quicker, less specific queries.

Connect HERE Mobility to Google ADK. Let your Gemini agents plan complex urban transit routes and analyze massive commute patterns.

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 Google ADK

Create your Vinkius account to connect HERE Mobility to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed transit data into Gemini

The `get_stations` tool locates transit stops near any corporate office coordinates stored in your BigQuery tables. Gemini agents need raw infrastructure data to route employees. You connect the MCP Server, and suddenly your model understands urban transit networks. Long-context reasoning fixes bulk logistics. You can dump a massive list of employee coordinates into the prompt. The agent iterates through `discover_trips` to calculate the exact public transit commute for every single person.

Multimodal planning at scale

The `search_multimodal_trips` tool calculates routes that combine short bike rides with long subway hauls. Cities run on mixed transport. Your agent gets a precise time breakdown for each mode so it can compare options. You filter which MCP tools the agent accesses using the `tool_names` parameter in Google ADK. If you only want it mapping local stops, restrict it to `get_nearby_stations` and `get_station_details` while blocking the heavier routing endpoints.

Monitor schedules via MCP Server

The `get_schedule` tool pulls live departure times for specific station IDs so commuters don't miss connections. Your Google Cloud agent hits the endpoint, filters for downtown-bound trains, and alerts users before they leave the building. When a user asks for a specific stop by name, the agent runs `get_stations_by_name`. It grabs the exact ID, then chains that into `get_route_details` to verify the entire trip path. Setting up the MCP Server takes just a few lines of code with `McpToolset`.

Setup guide

Set up HERE Mobility MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with HERE Mobility tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="HERE Mobility_agent",
    model="gemini-2.0-flash",
    instruction="You have access to HERE Mobility tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install `google-adk` via pip. Wrap your Vinkius endpoint URL in `StreamableHttpServerParameters` and pass it to `McpToolset`. Assign that toolset to your `LlmAgent` to expose the routing capabilities.

Yes. Your agent can pull lat/lng coordinates directly from BigQuery tables and feed them into the `discover_trips` tool. This allows you to generate transit plans for thousands of database records automatically.

The `get_nearby_stations` tool lets your agent define a custom search radius around a GPS point. The standard `get_stations` tool uses a fixed default radius for quicker, less specific queries.

Walking is supported as a component of larger journeys. The `search_multimodal_trips` endpoint calculates walking times when connecting a user from their origin to a transit hub, or between transfers.

The MCP Server processes exact latitude, longitude, and user departure times. Vinkius runs this environment in an ephemeral V8 Isolate Sandbox. Your API calls never persist on disk, and the authorization token grants zero access to your underlying Google Cloud infrastructure.

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