How to Use the Nominatim MCP in Google ADK

Q: Is there a way to confirm the Nominatim MCP server is running before my agent starts a job?

Absolutely. The getstatus tool is designed for this. Your agent can call it once at the start of a script to check for an 'OK' status and a low latency response.

Q: What's the best way to get detailed place information from Nominatim using a Google ADK agent?

Use a two-step process. First, use search to find a place and get its OSM ID. Then, pass that ID to the getdetails tool to get the full dataset, like its bounding box and importance score.

Connect your Gemini agents to OpenStreetMap with the Google ADK. Geocode addresses from BigQuery and enrich your cloud data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nominatim MCP to Google ADK

Create your Vinkius account to connect Nominatim 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 Nominatim with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Addresses into Map Data

The `search` tool gives your Gemini agent a direct way to convert addresses into coordinates. You can pull a column of addresses from a BigQuery table and have your agent geocode each one without managing API keys. Since Gemini models have a massive context window, you can feed your agent thousands of records. It can then reason about the results from multiple `search` calls to spot patterns or plan logistics routes without losing track.

Identify Locations from Coordinates

Use the `reverse_geocode` tool to find a street address for any latitude and longitude pair. This is for when your agent gets raw GPS data from a device or another Google Cloud service and needs to make sense of it. You can build a workflow in Vertex AI that triggers your agent. When new coordinate data lands in a Cloud Storage bucket, the agent automatically runs `reverse_geocode` and writes the resulting address back to a BigQuery table.

Query OSM Objects with Your Google ADK Agent

The `lookup_osm` and `get_details` tools let your agent dig into the raw OpenStreetMap dataset. You can get an object's bounding box, hierarchy, and other properties directly from its OSM ID. The Google ADK lets you filter which tools are exposed to an agent. You could create a specialized "geography expert" agent that only has access to this Nominatim MCP toolset, ensuring it stays focused on its task.

Setup guide

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

First, connect your agent to the Google Sheets API. Then, have it read the addresses and loop through them, calling the Nominatim `search` tool for each one to get the coordinates.

Absolutely. The `get_status` tool is designed for this. Your agent can call it once at the start of a script to check for an 'OK' status and a low latency response.

Use a two-step process. First, use `search` to find a place and get its OSM ID. Then, pass that ID to the `get_details` tool to get the full dataset, like its bounding box and importance score.

You'll need to implement a queueing mechanism. Since the public Nominatim API is limited, your agent's code should add a delay of at least one second between each call to the `search` tool.

Your query data, such as addresses or coordinates, is sent to the Vinkius server for processing only. The server is ephemeral, meaning the container it runs in is destroyed after use, and no request data is logged or retained.

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