How to Use the Geoapify MCP in Google ADK

Q: How do I filter which Geoapify tools are available to my agent?

When you initialize the McpToolset in the Google ADK, you can pass an optional toolnames filter. This lets you expose only the specific Geoapify tools you want a particular agent to have access to, like only geocodesearch and geocodereverse.

Q: What happens to my location data, like GPS coordinates, when I use Geoapify with Google ADK?

Your data, such as GPS coordinates for mapmatching or IP addresses for getipinfo, is sent to Geoapify through Vinkius's zero-trust infrastructure. Access is controlled by a single token, and your agent's execution is governed by your existing Google Cloud IAM policies.

Connect Gemini to real-world location data from Geoapify and act on your datasets in Google Cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geoapify MCP to Google ADK

Create your Vinkius account to connect Geoapify 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 Geoapify with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route Planning with BigQuery Data

Your agent can now directly bridge your Google Cloud data and the physical world. Let your Gemini agent pull a list of delivery addresses from a BigQuery table and feed them straight into Geoapify's `route_planner` tool. There's no need to write scripts to export and reformat data. Gemini's large context window means you can give the agent complex business rules right in the prompt. It can use `calculate_route_matrix` to evaluate dozens of potential driver-to-destination pairings from your dataset and find the most cost-effective solution in one shot.

Geo-enrich Your Vertex AI Models

Use agents to build better training data. An agent running on Google ADK can take a list of GPS coordinates from a project, use `geocode_reverse` to turn them into clean addresses, and then find demographic info with `get_boundaries_part_of`. This enriched data can be written back into BigQuery, ready for a Vertex AI training job. Imagine an agent that automatically finds competitor locations using `search_places` and calculates customer catchment areas with `calculate_isoline` to inform your next marketing campaign.

Your Google ADK MCP Server for Geoapify

This isn't just about maps, it's about giving your Google Cloud agent senses. It can find its own location via `get_ip_info` or check the elevation of a proposed job site with `get_elevation` before dispatching a crew. With the Google ADK, agents can react to events in your cloud infrastructure. A new row in a Spanner database can trigger an agent to use this MCP server, `calculate_route` for a field technician, and log the entire operation back to Google Cloud Logging. It connects your data to real-world action.

Setup guide

Set up Geoapify 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 Geoapify 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="Geoapify_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Geoapify 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 Geoapify. 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 Geoapify 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 Geoapify MCP in Google ADK

Your Gemini agent can query BigQuery using the native Google Cloud toolset, then pass the results directly into the Geoapify tools. For example, it can pull a list of addresses and feed them to `calculate_route_matrix` in the same workflow.

Yes, it's a perfect match. You can provide thousands of rows of location data or complex routing constraints in the prompt, and the Gemini model will maintain context while it uses the Geoapify tools to execute the task.

It brings powerful, third-party location intelligence directly into the secure Google Cloud environment. Your agents can act on your proprietary data in BigQuery and Vertex AI without it ever leaving your ecosystem, and all actions are logged and auditable.

When you initialize the `McpToolset` in the Google ADK, you can pass an optional `tool_names` filter. This lets you expose only the specific Geoapify tools you want a particular agent to have access to, like only `geocode_search` and `geocode_reverse`.

Your data, such as GPS coordinates for `map_matching` or IP addresses for `get_ip_info`, is sent to Geoapify through Vinkius's zero-trust infrastructure. Access is controlled by a single token, and your agent's execution is governed by your existing Google Cloud IAM policies.

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