How to Use the Radar MCP in Google ADK

Q: How do I add the Radar MCP Server to my Google ADK setup?

Install google-adk and define McpToolset with the Vinkius streamable HTTP server URL. Pass this toolset into your LlmAgent constructor to expose all ten location endpoints to your Gemini model.

Q: Can Google ADK agents search for nearby points of interest with Radar?

Yes, the searchplaces tool lets your agent find points of interest near specific coordinates. Your Google ADK client uses this to locate nearby distribution hubs or partner drop-off spots.

Q: How does Radar handle matrix routing calculations in Google ADK?

The calculateroutingmatrix tool handles multi-origin, multi-destination distance calculations. Your Google ADK agent triggers this tool to optimize fleet dispatching before querying your analytical models.

Q: Can I restrict which tools are exposed to my agent?

Yes, you can use the toolnames filter in your McpToolset configuration. This lets you restrict access to specific tools like validateaddress while hiding administrative endpoints.

Q: How is my address data secured when using Radar and Google ADK?

Every postal address sent to validateaddress is processed within ephemeral V8 isolates. Vinkius secures your API tokens, ensuring raw location strings are never stored or exposed to external networks.

Connect Google ADK agents to location tools to parse addresses and calculate routes directly alongside your BigQuery datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Radar MCP to Google ADK

Create your Vinkius account to connect Radar to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Radar with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Spatial Context for Google ADK Agents

`get_location_context` retrieves geofences and weather data for any coordinate point on the fly. Your Google ADK agent pulls this spatial context to make smarter routing decisions, matching physical weather conditions with active operational zones. This MCP Server outputs clean JSON payloads that your long-context Gemini models process without hitting token limits. The agent correlates this real-time location data with historical logistics records stored in BigQuery.

Geocoding Tools for Google ADK Workflows

`forward_geocode` converts raw, unstructured text addresses into precise latitude and longitude coordinates. Your Google ADK agent parses messy customer inputs from support tickets or database records and translates them into clean map coordinates. Integrating this MCP Server gives your enterprise agent direct access to global geocoding. The agent executes coordinate lookups, validates spatial accuracy, and writes the structured coordinates back to your Vertex AI pipeline.

IP Geolocation via Gemini Agents

`ip_geocode` extracts geographic coordinates and city data from a user's IP address. Your Google ADK agent uses this tool to instantly localize search queries, detect potential fraud, or verify user regions during session startup. Look, here's the thing: you don't need custom lookup databases. Just run the call through this MCP Server to feed region-specific data straight into your Gemini reasoning loop.

Setup guide

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

Install `google-adk` and define `McpToolset` with the Vinkius streamable HTTP server URL. Pass this toolset into your `LlmAgent` constructor to expose all ten location endpoints to your Gemini model.

Yes, the `search_places` tool lets your agent find points of interest near specific coordinates. Your Google ADK client uses this to locate nearby distribution hubs or partner drop-off spots.

The `calculate_routing_matrix` tool handles multi-origin, multi-destination distance calculations. Your Google ADK agent triggers this tool to optimize fleet dispatching before querying your analytical models.

Yes, you can use the `tool_names` filter in your `McpToolset` configuration. This lets you restrict access to specific tools like `validate_address` while hiding administrative endpoints.

Every postal address sent to `validate_address` is processed within ephemeral V8 isolates. Vinkius secures your API tokens, ensuring raw location strings are never stored or exposed to external networks.

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