How to Use the iFood MCP in Vercel AI SDK

Q: How do I manage multiple restaurant locations using Vercel AI SDK?

Your code calls getstores to pull the active location IDs. From there, the agent can query getstoredetails or adjust schedules via updatebusinesshours on the fly.

Stream iFood order statuses and catalog updates directly into your React components using the iFood MCP Server 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 iFood MCP to Vercel AI SDK

Create your Vinkius account to connect iFood 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 iFood with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Order Feeds for Vercel AI SDK

Your interface needs to show incoming orders without spinning wheels. By pairing this MCP Server with Vercel AI SDK's streaming capabilities, your UI updates the moment a customer pays, rendering items retrieved via `get_orders` directly in the user's viewport. This setup bypasses standard polling bottlenecks. Your agent calls `get_order_details` to verify the kitchen's prep list, and the raw JSON streams straight into your React server components, giving dispatchers instant visibility.

Live Menu Adjustments at the Edge

Changing prices during a dinner rush shouldn't require a full page reload. When your agent invokes `update_catalog_item` through the Vercel AI SDK, the updated price and availability status reflect immediately in your custom merchant dashboard. The SDK handles the streaming UI state, while the underlying server executes the catalog fetch via `get_catalog`. This ensures your staff sees the live menu structure without waiting for a database sync.

Interactive Delivery Tracking Components

Customers want to see where their food is right now. This MCP integration lets you stream live courier coordinates and status changes using `get_logistics` directly into your Next.js frontend. When the agent calls `update_order_status` to mark an order as dispatched, the UI transitions instantly. No lag, no manual refreshes, just a clean operational feed powered by Edge-compatible streams.

Setup guide

Set up iFood 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 iFood 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 iFood 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 iFood. 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 iFood 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 iFood MCP in Vercel AI SDK

It hooks directly into the streaming text functions. When your agent calls `get_orders`, the JSON payload streams in chunks, allowing your React components to render order cards incrementally.

Yes. You can bind a button to an action that lets your agent call `assign_driver`. The result of the assignment streams back to confirm the courier's status in real-time.

Your code calls `get_stores` to pull the active location IDs. From there, the agent can query `get_store_details` or adjust schedules via `update_business_hours` on the fly.

No. Vinkius hosts the infrastructure, meaning your Next.js edge routes connect directly to our zero-trust sandbox using a single token.

Absolutely. Vinkius runs every request through isolated V8 sandboxes. Your sensitive delivery coordinates and catalog prices are never stored, and OAuth tokens are completely encrypted.

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