How to Use the FNS SNAP Retailer Locator (USDA) MCP in Google ADK

Q: How do I configure the FNS SNAP Retailer Locator (USDA) inside Google ADK?

Use the McpToolset class with StreamableHttpServerParameters pointing to your Vinkius endpoint. Pass the toolset instance directly into your LlmAgent. The Gemini model will automatically detect searchretailers and run queries when needed.

Q: How does the FNS SNAP Retailer Locator (USDA) handle large payloads in Google ADK?

The searchretailersbylocation tool returns structured JSON data containing merchant details. Because Gemini models have huge token limits, you can pass these large coordinate-based payloads directly into the agent's context without truncation.

Q: Can I restrict Google ADK to only use specific tools from this MCP server?

Yes, you can use the optional toolnames filter when initializing your McpToolset. This lets you restrict the agent to just searchretailers if you want to block coordinate-based radius searches. It prevents your agent from drifting off-task.

Connect the FNS SNAP Retailer Locator (USDA) MCP Server to your Google ADK pipelines for enterprise-grade geographic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FNS SNAP Retailer Locator (USDA) MCP to Google ADK

Create your Vinkius account to connect FNS SNAP Retailer Locator (USDA) 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 FNS SNAP Retailer Locator (USDA) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise SNAP Search with Google ADK

The `search_retailers` tool gives your Gemini-powered agent direct access to USDA merchant records via this MCP server. The Google ADK agent reads the SNAP store names and locations directly from the official USDA dataset. This Google ADK integration allows you to combine public benefits data with your internal enterprise databases. You can feed the output of your USDA store queries directly into other Google Cloud systems. It makes building geographic SNAP search agents with Google ADK straightforward.

Large-Context Location Filtering

The `search_retailers_by_location` tool pulls all SNAP-authorized stores within a set mile radius of any coordinate. Your Google ADK agent can ingest this entire USDA list and perform complex reasoning over the whole batch. Instead of paging through USDA results, your Gemini model analyzes the spatial data in a single prompt. This is ideal for mapping USDA merchant density or identifying food deserts. The tool handles the coordinate lookup, and Google ADK processes the massive payload.

Vertex AI and BigQuery Integration

This MCP server integrates public benefits data directly with your enterprise BigQuery datasets. Run a BigQuery query to find areas with low food access, then have your Google ADK agent call `search_retailers` to check nearby merchants. The Google ADK handles the handoff between your cloud database and the USDA public API. Because Vinkius manages the authentication, your Google ADK agent only needs a single MCP server token. This simplifies your IAM policies when querying USDA data via Google ADK.

Setup guide

Set up FNS SNAP Retailer Locator (USDA) 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 FNS SNAP Retailer Locator (USDA) 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="FNS SNAP Retailer Locator (USDA)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to FNS SNAP Retailer Locator (USDA) 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 USDA FNS. 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 FNS SNAP Retailer Locator (USDA) 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 FNS SNAP Retailer Locator (USDA) MCP in Google ADK

Use the `McpToolset` class with `StreamableHttpServerParameters` pointing to your Vinkius endpoint. Pass the toolset instance directly into your `LlmAgent`. The Gemini model will automatically detect `search_retailers` and run queries when needed.

Yes, the ADK supports both Stdio and HTTP transports. For cloud-hosted enterprise agents, the HTTP transport is recommended as it connects directly to the managed Vinkius hosting. This setup avoids local process management overhead.

The `search_retailers_by_location` tool returns structured JSON data containing merchant details. Because Gemini models have huge token limits, you can pass these large coordinate-based payloads directly into the agent's context without truncation.

Yes, you can use the optional `tool_names` filter when initializing your `McpToolset`. This lets you restrict the agent to just `search_retailers` if you want to block coordinate-based radius searches. It prevents your agent from drifting off-task.

Yes, all transport layers are secured with TLS encryption. Your latitude, longitude, and zip code parameters are processed in memory and never written to disk. The only data processed is the public USDA SNAP retailer address and coordinate data required to return your search results.

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