How to Use the Smarty MCP in Google ADK

Q: How does Smarty help my Google ADK process US addresses?

Your agent uses validateusaddress to get DPV status and coordinates for any US address. Since you're building on Google Cloud, this precise location data integrates easily with other services in the Vertex AI suite.

Q: What if I need Smarty to extract addresses using my Google ADK?

Simply pass the raw text to extractaddresses. The function pulls out physical addresses from documents or emails, making that unstructured data available for your BigQuery analysis. It's a reliable way to populate messy datasets.

Q: What account information does Smarty give my Google ADK?

The agent uses getaccountinfo when it needs context about the user or system running the job. This helps ensure that your LlmAgent respects necessary operational limits before executing a data write.

Build enterprise agents on Google Cloud using the Smarty MCP Server for data quality.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Smarty MCP to Google ADK

Create your Vinkius account to connect Smarty 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 Smarty with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate US addresses with DPV

The `validate_us_address` tool checks a US street address and gives you the Delivery Point Validation (DPV) status plus coordinates. This means your BigQuery-backed agent isn't just guessing; it confirms the precise delivery point. It’s perfect for agents that need to tie location data directly into Google Cloud infrastructure, making sure all records are geographically accurate.

Handle global addresses

When your agent runs on Gemini and encounters international data, use `validate_intl_address`. You pass the address line and country, and the tool validates and geocodes it. This keeps your long-context reasoning process running smoothly globally. It’s a solid guardrail against foreign or non-standard postal systems corrupting your BigQuery inputs.

Parse addresses from raw text

Sometimes the address is mixed into user input, not in a dedicated field. The `extract_addresses` function pulls physical addresses out of documents or emails, alongside other data types like phone numbers and URLs. Your agent gets clean, actionable data. This tool prevents your LlmAgent from failing just because the raw text wasn't structured perfectly.

Setup guide

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

Your agent uses `validate_us_address` to get DPV status and coordinates for any US address. Since you're building on Google Cloud, this precise location data integrates easily with other services in the Vertex AI suite.

Yes. If your agent needs to process international data, it calls `validate_intl_address`. You provide the address line and country, and the tool handles validation and geocoding for global compliance.

Simply pass the raw text to `extract_addresses`. The function pulls out physical addresses from documents or emails, making that unstructured data available for your BigQuery analysis. It's a reliable way to populate messy datasets.

The agent uses `get_account_info` when it needs context about the user or system running the job. This helps ensure that your LlmAgent respects necessary operational limits before executing a data write.

This MCP Server is designed to handle physical address information (US and international formats). It validates, extracts, and geocodes location intelligence, which is critical for any workflow dealing with global user inputs.

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