How to Use the Geocodio MCP in Google ADK

Q: How do I add Geocodio tools to a Google ADK agent?

You import McpToolset from the ADK and initialize it with the Geocodio server URL. Then, you pass this toolset into the tools list when creating your LlmAgent.

Q: How do I restrict my Google ADK agent to only use certain Geocodio functions?

When you create the McpToolset for Geocodio, use the toolnames parameter. It takes a list of strings, so you can specify exactly which tools, like geocodeusaddress, are exposed to the agent.

Let your Google ADK agents enrich BigQuery data with Geocodio's US/Canada geocoding and census info.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geocodio MCP to Google ADK

Create your Vinkius account to connect Geocodio 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 Geocodio with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Geocode Data Directly from BigQuery

Your agent is already connected to Google Cloud. Now it can pull a column of addresses from a BigQuery table, feed them into Geocodio's `batch_geocode_addresses` tool, and get back coordinates. This closes the loop without moving data out of your GCP project. The Gemini models' long-context window is perfect for this. Your agent can hold a massive list of addresses in memory, process them with a single `batch_enriched_geocode` call, and then write the enriched data—like census tracts and timezones—back to a new BigQuery table.

Enrich Datasets with Legislative Data

Go beyond simple geocoding. Your Google ADK agent can take a list of coordinates and use `batch_enriched_reverse` to append specific data fields like congressional districts. This is for building serious business or policy analysis tools. You can check what's available anytime by having your agent call `list_schema_fields`. This gives you an up-to-date list of all the data points Geocodio offers, so you can adapt your agent's logic to pull new fields as they become available.

Filter Tools for Enterprise Agents

The Google ADK `McpToolset` lets you be specific. Use the `tool_names` filter to expose only certain Geocodio tools to your agent, like `geocode_us_address` and `reverse_geocode`. This is how you enforce focus for enterprise-grade agents. This MCP server handles the connection and auth. Your agent just uses the toolset you've defined. It's a clean way to add third-party tools to your Google Cloud-native agent without managing another piece of infrastructure.

Setup guide

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

You import `McpToolset` from the ADK and initialize it with the Geocodio server URL. Then, you pass this toolset into the `tools` list when creating your `LlmAgent`.

Absolutely. Your Gemini-powered agent can query addresses from BigQuery, pass them to the Geocodio `batch_geocode_addresses` tool, and then write the resulting coordinates and enriched data back to another table.

When you create the `McpToolset` for Geocodio, use the `tool_names` parameter. It takes a list of strings, so you can specify exactly which tools, like `geocode_us_address`, are exposed to the agent.

It lets your agent, which is already integrated with your Google Cloud data, access external location data without custom integrations. You can geocode addresses from BigQuery or Cloud Storage and get results back in the same workflow.

The Google ADK agent sends address data to the managed MCP server over a secure connection. The server, running in a zero-trust environment, processes the request and doesn't store your query data. This isolates the geocoding task from your core GCP 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