How to Use the Cornershop MCP in Vercel AI SDK

Q: How does Cornershop stream live store inventories to the Vercel AI SDK?

You pass liststores and searchproducts to the SDK's streaming text functions. The model fetches inventory data from local LatAm retailers and streams the results directly to your React components, bypassing the need for a separate polling server.

Q: Can I handle grocery cart updates in real-time using Vercel AI SDK and Cornershop?

Yes, you can. By exposing updateorder to the streaming interface, your Vercel AI SDK app lets users swap items or change quantities dynamically as the model processes the request on the edge.

Q: Can my Vercel AI SDK application cancel a Cornershop grocery run before it gets picked?

You can, provided you call cancelorder before the shopper begins. The model checks the order status and executes the cancellation directly through your edge route.

Let your Vercel AI SDK app search LatAm grocery shelves and place orders in real-time with this Cornershop MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cornershop MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live grocery feeds with Vercel AI SDK

Your users don't want to wait for a full page reload to see what's in stock at Jumbo or Lider when using this MCP Server's `list_stores` and `search_products` tools. By passing these tools directly to your Vercel AI SDK streaming text functions, your UI displays local store inventories as the model finds them. The raw grocery data feeds straight into your React component state, letting shoppers compare prices instantly. When a customer changes their mind, the active Cornershop order updates live on your Vercel AI SDK frontend. You can pipe `update_order` directly into your Next.js edge route, giving your interface the power to swap out out-of-stock items on the fly without making the shopper wait for a background sync.

Instant checkout pipelines

Placing Cornershop grocery orders requires precise payload structures that `create_order` handles directly inside your Vercel AI SDK application. This MCP Server maps those grocery structures directly to your streaming functions, allowing the model to execute checkout with the exact JSON payload required for LatAm delivery. Because the Vercel AI SDK handles tool calls natively, your agent pulls delivery addresses and cart items from your local state, matches them to `get_product` details, and confirms the checkout before a human has to click a single button.

Real-time driver and delivery tracking

Tracking active deliveries is straightforward when you hook up `track_order` and `list_shoppers` to your Vercel AI SDK edge functions. Your streaming UI gets immediate access to the shopper's name and current coordinates, updating your map components live. If something goes wrong with the delivery, your Vercel AI SDK interface can trigger `cancel_order` instantly. This stops the grocery run before the picker even starts grabbing items from the shelves.

Setup guide

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

You pass `list_stores` and `search_products` to the SDK's streaming text functions. The model fetches inventory data from local LatAm retailers and streams the results directly to your React components, bypassing the need for a separate polling server.

Yes, you can. By exposing `update_order` to the streaming interface, your Vercel AI SDK app lets users swap items or change quantities dynamically as the model processes the request on the edge.

The SDK imports the server's schema directly. When the model invokes `get_product` or `get_store`, the Vercel AI SDK translates the JSON response into immediate UI renders without extra parsing.

You can, provided you call `cancel_order` before the shopper begins. The model checks the order status and executes the cancellation directly through your edge route.

Your LatAm delivery addresses and order details never touch external logs. They pass through our secure V8 sandbox directly to the Uber delivery infrastructure, keeping your physical location data private.

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