How to Use the USDA FoodData Central MCP in Google ADK

Q: How does the Google ADK connect to USDA FoodData Central?

You pass the MCP Server endpoint into the LlmAgent constructor. The agent then uses tools like searchusdafoods to interact with the data source, making it feel like native BigQuery integration.

Q: Are there limits on how many foods I can check with USDA FoodData Central using this MCP Server?

The searchusdafoods tool accesses a database of over 300,000 items. The ability to handle large volumes is one of the reasons it's built for enterprise scale.

Act on USDA FoodData Central nutrition data using Google ADK for enterprise agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect USDA FoodData Central MCP to Google ADK

Create your Vinkius account to connect USDA FoodData Central 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 USDA FoodData Central with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get deep nutrient details by ID

Need specific nutritional breakdowns? Use the `get_usda_food_details` tool to pull comprehensive info based on a USDA FDC ID. The agent gets structured, scientific-grade data directly from the FoodData Central MCP Server. Since your agents are running on Google Cloud and integrating with BigQuery, this clean output feeds perfectly into existing datasets for analysis.

Search 300k+ foods across enterprise data

Start broad searches using `search_usda_foods`. This tool queries over 300,000 USDA items and gives you a quick look at calories, protein, fat, carbs, fiber, and sugar. It covers both general goods and specific branded products. This mechanism means your Google ADK agent can surface massive amounts of market data without needing manual data prep.

Build multi-step, enterprise workflows

Your agents don't stop after one call. They can chain the search (`search_usda_foods`) and then immediately pull details using `get_usda_food_details`. The Google ADK manages this flow across 1M+ tokens of context. This capability is huge for enterprise use cases, letting your agents perform complex data operations on the USDA FoodData Central without failure.

Setup guide

Set up USDA FoodData Central 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 USDA FoodData Central 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="USDA FoodData Central_agent",
    model="gemini-2.0-flash",
    instruction="You have access to USDA FoodData Central 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. 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 USDA FoodData Central 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 USDA FoodData Central MCP in Google ADK

You pass the MCP Server endpoint into the `LlmAgent` constructor. The agent then uses tools like `search_usda_foods` to interact with the data source, making it feel like native BigQuery integration.

Yes. Since your agents support long-context reasoning, they can perform multi-step analyses—for instance, searching for a food group and then pulling the detailed nutrient profile for each item found in the USDA FoodData Central.

The agent framework is built for enterprise safety. It validates actions before execution, ensuring that any nutrient data returned by the MCP Server fits into your existing BigQuery schema.

The `search_usda_foods` tool accesses a database of over 300,000 items. The ability to handle large volumes is one of the reasons it's built for enterprise scale.

The server touches public nutritional profile data from the U.S. Department of Agriculture, specifically nutrient metrics associated with food items and their IDs.

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