How to Use the FNS SNAP Retailer Locator (USDA) MCP in OpenAI Agents SDK

Q: How do I initialize the FNS SNAP Retailer Locator (USDA) with the OpenAI Agents SDK?

Install the package and spin up the MCPServerStreamableHttp client using the provided Vinkius endpoint. Pass this server object into your agent's constructor. The SDK automatically registers searchretailers and searchretailersbylocation without extra code.

Let your OpenAI Agents SDK production agents query USDA SNAP retailer data with built-in guardrails and automatic tool discovery.

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 OpenAI Agents SDK

Create your Vinkius account to connect FNS SNAP Retailer Locator (USDA) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Locate SNAP Retailers with OpenAI Agents SDK

The `search_retailers` tool lets your agents query live USDA public data to find authorized food merchants. By calling `search_retailers`, your system pulls exact store records using attributes like zip codes or state lines. This isn't a mock setup; it connects your OpenAI Agents SDK production pipeline to real USDA SNAP datasets instantly. You configure this MCP server by passing the endpoint directly to your OpenAI Agents SDK constructor. The OpenAI Agents SDK automatically discovers the USDA tools without manual schema mapping. You get clean, structured SNAP merchant data back without writing custom API wrappers.

Spatial Queries via Coordinates

The `search_retailers_by_location` tool handles coordinate-based filtering to find stores near a user. Your OpenAI Agents SDK agent handles the math, sending precise coordinates to the USDA database. This setup works well for mobile-first deployments querying USDA merchants. Because the OpenAI Agents SDK manages the streamable HTTP connection, your agent resolves spatial queries on the fly. You don't have to manage complex spatial indexing for SNAP retailers on your own servers.

Guarded Federal Data Access

This MCP server integrates directly with your OpenAI Agents SDK guardrails to validate USDA queries before they run. If your OpenAI Agents SDK agent tries to pass an invalid zip code format to the USDA tool, the guardrail stops it. You can trace every single USDA query through the OpenAI developer dashboard. This gives you a clear view of how your OpenAI Agents SDK agents interact with the USDA dataset. It keeps your operational costs predictable and prevents bad USDA queries from hitting rate limits.

Setup guide

Set up FNS SNAP Retailer Locator (USDA) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all FNS SNAP Retailer Locator (USDA) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives FNS SNAP Retailer Locator (USDA) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate FNS SNAP Retailer Locator (USDA) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="FNS SNAP Retailer Locator (USDA) Agent",
            instructions="You have access to FNS SNAP Retailer Locator (USDA) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package and spin up the `MCPServerStreamableHttp` client using the provided Vinkius endpoint. Pass this server object into your agent's constructor. The SDK automatically registers `search_retailers` and `search_retailers_by_location` without extra code.

Yes, you can control tool access at the agent constructor level. If you only want your agent to perform coordinate lookups, expose only `search_retailers_by_location`. This keeps your agent focused and prevents unnecessary token usage.

The MCP server runs inside a managed V8 sandbox on Vinkius, which handles connection pooling. To optimize performance, set `cacheToolsList=True` in your SDK configuration. This prevents your agent from refetching the tool definitions on every single turn.

Yes, you must use the async context manager provided by the SDK. This allows your agent to run multiple `search_retailers` queries in parallel without blocking the main event loop. It is built for high-throughput production environments.

Vinkius processes all requests in ephemeral, zero-trust sandboxes. Your coordinate inputs and store name search queries are never stored or logged permanently. Only the raw USDA SNAP retailer address and coordinate data are returned to your local OpenAI Agents SDK runtime.

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