How to Use the HERE (Location & Maps) MCP in Google ADK

Connect Gemini agents on Google Cloud to real-world location data using the Google ADK and this HERE MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HERE (Location & Maps) MCP to Google ADK

Create your Vinkius account to connect HERE (Location & Maps) 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 (Location & Maps) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route Against Your BigQuery Data

This is where it gets interesting. Your ADK agent can pull a list of 10,000 customer addresses from a BigQuery table, then feed them into the `calculate_routing_matrix` tool. You get back an optimized delivery plan for your entire fleet, all kicked off by a single prompt. Gemini's large context window means your agent can reason over massive datasets. It can hold the entire routing matrix result in its head while cross-referencing it with vehicle capacity and driver schedules from another database. This MCP setup connects your cloud data to ground truth.

Find Your Next Business Location

Site selection is a perfect job for an agent. It can analyze customer postal codes in BigQuery, find the geographic center, and then use `calculate_v8_isoline` to see which commercial properties are within a 15-minute drive for 80% of your customers. An isoline shows the area you can reach within a certain time or distance. Your agent can run multiple scenarios—'What if we move it two blocks east?'—and generate maps showing the impact. It's a powerful way to use your existing Google Cloud data to make physical-world decisions.

Geocode Addresses with Google ADK

Turn your raw data into map-ready coordinates. Your ADK agent can be triggered by new rows in a Google Sheet or BigQuery table, grab the address column, and use `forward_geocode` to get a precise latitude and longitude. The agent then writes the result right back to the table. This creates a clean, reliable location dataset inside your Google Cloud project. You're not just running one-off queries; you're building an automated data pipeline. The agent can also use `reverse_geocode` to turn raw GPS logs from IoT devices into clean street addresses.

Setup guide

Set up HERE (Location & Maps) 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 (Location & Maps) 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 (Location & Maps)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to HERE (Location & Maps) 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 Technologies. 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 (Location & Maps) 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 (Location & Maps) MCP in Google ADK

Yes. Your agent can read a column of addresses from BigQuery, call the `forward_geocode` tool for each one, and write the resulting coordinates back to a new column. This is a common pattern for cleaning up location data.

It allows an agent to handle large, complex planning tasks. For example, it can process the entire output of a `calculate_routing_matrix` for hundreds of points without losing track of the goal, making it ideal for large-scale logistics.

It acts as a bridge. The Google ADK lets your agent access your data in BigQuery and other GCP services, and this server gives that same agent the tools to act on that data in the real world—calculating routes, finding places, and checking traffic.

An isoline is a shape on a map showing how far you can travel from a point in a set time. Your agent calls `calculate_v8_isoline` with a coordinate and a duration (like '15 minutes'), and gets back a polygon. It's good for market analysis or emergency response planning.

The Vinkius platform processes requests in a zero-trust, ephemeral environment. Only the specific data your agent sends—like a list of addresses for geocoding—is passed to the tool. The server has no access to your broader BigQuery dataset.

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