How to Use the Google Maps MCP in Google ADK

Q: How do I register the Google Maps MCP Server in Google ADK?

Use McpToolset with StreamableHttpServerParameters pointing to your Vinkius endpoint. Pass this toolset directly to your LlmAgent constructor. The ADK handles the connection over HTTP or Stdio automatically.

Q: Can Google ADK agents filter specific Google Maps tools?

Yes, you can use the optional toolnames filter when initializing the toolset. This lets you restrict your Google ADK agent to only use geocode or directions, blocking access to search tools if your workflow doesn't need them.

Hook up Google Maps to your Google ADK pipelines to feed real-time coordinates and ETAs directly into Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Maps MCP to Google ADK

Create your Vinkius account to connect Google 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 Google Maps with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Clean geocoding for Google ADK data pipelines

If you have millions of customer addresses sitting in BigQuery, your Google ADK agent can process them in batches. It calls `geocode` to turn raw address strings into precise latitude and longitude coordinates. Because Gemini handles massive token contexts, you can feed thousands of these coordinates back into your agent's memory for deep spatial analysis. This setup lets you run heavy location intelligence tasks without writing custom API wrappers. The ADK handles the transport, while the Google Maps MCP Server does the heavy lifting of resolving messy, unstructured location data.

Targeted business search inside Vertex AI

Your enterprise agent can scan entire cities using `place_search` to identify competitors, partners, or service hubs. It grabs local listings based on natural language queries, and then uses `place_details` to extract deep metadata like business hours and customer ratings. This structured data goes straight into Gemini's reasoning engine. The agent can cross-reference these Google Maps details with your internal Google Cloud databases, giving you a clear picture of local market conditions without leaving your secure cloud environment.

Enterprise route planning with Gemini reasoning

Logistics agents need accurate travel times to schedule deliveries. By invoking `directions` through the MCP Server, your ADK agent gets real-world drive times and route distances between multiple coordinates. Gemini uses this data to optimize dispatch schedules, matching the best route to the right driver. Using this MCP toolset means your agent reads live traffic data instead of relying on static, outdated mapping files. You get dynamic routing that updates based on real-world conditions, all managed through your existing Google Cloud infrastructure.

Setup guide

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

Use `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius endpoint. Pass this toolset directly to your `LlmAgent` constructor. The ADK handles the connection over HTTP or Stdio automatically.

Yes, you can use the optional `tool_names` filter when initializing the toolset. This lets you restrict your Google ADK agent to only use `geocode` or `directions`, blocking access to search tools if your workflow doesn't need them.

Gemini's million-token context window easily digests large payloads from `place_search`. The ADK passes the raw JSON response directly to the model, allowing the agent to analyze hundreds of venue details simultaneously without running out of memory.

Yes. The Vinkius-managed server supports both SSE and Stdio transport protocols. You can run the connection locally for testing and then switch to the hosted HTTP endpoint when deploying your agent to Google Cloud.

Vinkius routes all address lookups and route coordinates through isolated V8 sandboxes. We secure your API tokens at rest, ensuring that third parties never see sensitive shipping addresses or client locations during transit.

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