How to Use the USDA FoodData Central MCP in Vercel AI SDK

Q: How do I search for foods using USDA FoodData Central and Vercel AI SDK?

You call searchusdafoods through the MCP client. The agent returns a list of 300,000+ foods, giving you quick access to basic metrics like calories and carbs in real-time.

Q: Can I get detailed nutritional info for a single food using USDA FoodData Central and Vercel AI SDK?

Yep. Use getusdafooddetails by providing the specific USDA FDC ID. This delivers comprehensive, scientific-grade data on one item's nutrient profile.

See USDA FoodData Central nutrition results streaming live into your Next.js app with Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect USDA FoodData Central to Vercel AI 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 USDA FoodData Central with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Nutritional Data via MCP Server

When a user clicks 'Check Nutrition,' the agent runs `search_usda_foods`. Instead of waiting for a full response, your UI streams calorie counts, protein amounts, and fiber data as they appear. This makes the whole process feel fast and responsive. It's perfect for building user-facing tools where latency matters. The MCP tool results stream directly into the React component, giving instant feedback that doesn't require a loading spinner.

Pinpoint Food Details with Vercel AI SDK

Need specific nutrient breakdowns? Use `get_usda_food_details` by feeding it an USDA FDC ID. This tool pulls scientific-grade data for a single food item, detailing its exact sugar content or fat levels. This is crucial for comparison tools. Your client can check multiple IDs and display the detailed nutrition profile immediately in the UI.

Building MCP Tools with Vercel AI SDK

The `ai-sdk` handles calling external services like USDA FoodData Central without cluttering your frontend code. You call `mcpClient.tools()` and pass those tools to `streamText`. The server handles the heavy lifting. It’s clean, efficient architecture for building products that interact with specialized databases.

Setup guide

Set up USDA FoodData Central MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all USDA FoodData Central tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent USDA FoodData Central transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You call `search_usda_foods` through the MCP client. The agent returns a list of 300,000+ foods, giving you quick access to basic metrics like calories and carbs in real-time.

Yep. Use `get_usda_food_details` by providing the specific USDA FDC ID. This delivers comprehensive, scientific-grade data on one item's nutrient profile.

Absolutely. Since your client uses streaming methods, the tool results stream directly into your React component as they arrive. This is key for a smooth user experience.

It exposes nutritional data: calories, protein, fat, carbs, fiber, and sugar. The underlying database covers everything from foundation foods to branded products.

The server accesses public nutritional data types: nutrient profiles (e.g., protein, sugar) linked by USDA FDC IDs. No private user or personal identifiers are involved.

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