How to Use the LocationIQ (Geocoding & Maps) MCP in Google ADK

Q: How do I connect LocationIQ (Geocoding & Maps) to Google ADK?

Use McpToolset with StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset directly into your LlmAgent to expose all ten spatial tools via MCP.

Q: Can I limit which LocationIQ (Geocoding & Maps) tools are exposed to Google ADK?

Yes, use the optional toolnames filter in the toolset configuration to expose only specific tools like reversegeocode or calculatedirections. This keeps the context window clean and prevents Gemini from invoking unused mapping endpoints.

Q: How do I verify my remaining API credits within my Google Cloud pipeline?

Call checkaccountbalance to retrieve your active OpenStreetMap query balance. You can log this balance directly to Cloud Logging to monitor your ingestion costs.

Ground your Gemini enterprise models with LocationIQ (Geocoding & Maps) spatial data over a secure MCP server connection.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LocationIQ (Geocoding & Maps) MCP to Google ADK

Create your Vinkius account to connect LocationIQ (Geocoding & 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 LocationIQ (Geocoding & Maps) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery Spatial Data Grounding

The `search_geocode` tool converts address strings from your BigQuery tables into precise latitude and longitude coordinates. Google ADK feeds this coordinate data directly into Gemini's long-context window for spatial reasoning. To keep processing efficient, your Google ADK pipeline uses `search_country_filter` to restrict coordinates to specific operational regions before passing them to Gemini. This limits the data footprint before you run downstream clustering algorithms in Vertex AI.

Enterprise Routing via MCP Server

The `calculate_directions` tool generates optimal driving, walking, or cycling paths based on live OpenStreetMap data. Your Google ADK agent parses these routes to calculate shipping ETAs for complex supply chain pipelines. When dealing with multiple distribution hubs, `calculate_distance_matrix` builds travel duration tables across your entire fleet. The MCP server handles the HTTP transport, allowing your Gemini models to reason over massive logistics matrices.

Reverse Geocoding for Warehouse Logs

The `reverse_geocode` tool translates GPS coordinates from delivery trucks back into clean, human-readable postal addresses. By calling `reverse_language_bias`, your Google ADK agent localizes these addresses for regional logistics managers. If coordinates from mobile devices are slightly off, `snap_nearest_roads` corrects them to the nearest physical street. This ensures your BigQuery records contain accurate road-aligned coordinates instead of raw, noisy GPS points.

Setup guide

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

Use `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset directly into your `LlmAgent` to expose all ten spatial tools via MCP.

Yes, use the optional `tool_names` filter in the toolset configuration to expose only specific tools like `reverse_geocode` or `calculate_directions`. This keeps the context window clean and prevents Gemini from invoking unused mapping endpoints.

Gemini leverages its 1M+ token context to analyze massive coordinate tables returned by `calculate_distance_matrix`. The model can cross-reference these distance matrices with your warehouse inventory data in a single reasoning step.

Call `check_account_balance` to retrieve your active OpenStreetMap query balance. You can log this balance directly to Cloud Logging to monitor your ingestion costs.

Your raw geocoordinates and address strings are processed in memory within an ephemeral V8 sandbox container. No location payloads or API tokens are written to persistent storage, maintaining strict enterprise data isolation.

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