How to Use the Edamam Extended MCP in Vercel AI SDK

Q: How do I search for vegan recipes using Edamam Extended and Vercel AI SDK?

You call searchrecipes by passing the vegan health filter inside your tool call configuration. The Vercel AI SDK streams the matching recipes directly to your frontend as structured UI components. This eliminates the need for manual parsing on your server.

Q: Can I analyze raw ingredient text with Edamam Extended in Vercel AI SDK?

Yes, you use the analyzenutrition tool to submit unformatted ingredient lists. The MCP Server processes the text and returns a structured JSON payload with full macro breakdowns. Your application can stream this output directly to Next.js components.

Q: How do I handle database lookups for specific food items using Edamam Extended and Vercel AI SDK?

You query the parsefood tool with the ingredient name or UPC code. The SDK receives the verified food data from the 900,000-item database in real-time. Make sure to call mcpClient.close() when your edge function completes the request.

Q: What is the easiest way to initialize this MCP Server in my Next.js project?

Install @ai-sdk/mcp and initialize the client using createMCPClient with your Vinkius HTTP endpoint. Pass the tools directly into generateText or streamText to let your agent access the food database.

Stream raw food data and meal ideas straight to your frontend with Edamam Extended and 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 Edamam Extended MCP to Vercel AI SDK

Create your Vinkius account to connect Edamam Extended 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 Edamam Extended with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live recipe search without loading spinners

`search_recipes` pulls from a database of 3 million recipes directly into your live user interface. You pass user dietary filters straight to the API, and the results render in real-time as the text streams. This setup removes the lag of traditional API polling. Your interface stays responsive because the MCP Server handles the raw payload parsing on the Vinkius edge, sending only the structured food data your UI needs.

Real-time nutrition analysis using Vercel AI SDK

`analyze_nutrition` calculates exact macronutrient profiles for any recipe text your users input. The AI client processes the raw ingredient list and returns structured caloric and vitamin data instantly. By using this MCP Server, your edge functions avoid heavy processing overhead. The client streams the structured JSON directly into your React or Next.js components, letting users see the macro breakdown update as they type.

Instant ingredient lookups

`parse_food` checks a database of 900,000 items to identify ingredients and extract their direct nutritional values. Your application matches user search terms against verified database entries without building a custom backend. You configure this by calling `createMCPClient` and passing the tools directly to `streamText`. The connection handles the heavy lifting, sending clean food data straight to your user's viewport.

Setup guide

Set up Edamam Extended 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 Edamam Extended 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 Edamam Extended 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 Edamam. 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 Edamam Extended 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 Edamam Extended MCP in Vercel AI SDK

You call `search_recipes` by passing the vegan health filter inside your tool call configuration. The Vercel AI SDK streams the matching recipes directly to your frontend as structured UI components. This eliminates the need for manual parsing on your server.

Yes, you use the `analyze_nutrition` tool to submit unformatted ingredient lists. The MCP Server processes the text and returns a structured JSON payload with full macro breakdowns. Your application can stream this output directly to Next.js components.

You query the `parse_food` tool with the ingredient name or UPC code. The SDK receives the verified food data from the 900,000-item database in real-time. Make sure to call `mcpClient.close()` when your edge function completes the request.

Install `@ai-sdk/mcp` and initialize the client using `createMCPClient` with your Vinkius HTTP endpoint. Pass the tools directly into `generateText` or `streamText` to let your agent access the food database.

The MCP Server processes ingredient lists and recipe text inside an ephemeral, zero-trust sandbox. Your raw nutritional queries are never stored or used to train public models. Vinkius secures the entire transport layer using single-token endpoint authentication.

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