How to Use the VTEX Catalog MCP in Vercel AI SDK

Q: Can I use Vercel AI SDK to update inventory in the VTEX Catalog?

Yeah, you can. By calling managestock, your agent updates the available quantity of any SKU. This action happens live and is ideal for building checkout or fulfillment tools.

Q: Does Vercel AI SDK support retrieving brand details from VTEX Catalog?

Absolutely. Use getbrand to fetch all the necessary information about a specific brand. The results stream in, letting your frontend build out branded content right away.

Get product data and manage inventory in real time with the 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 VTEX Catalog MCP to Vercel AI SDK

Create your Vinkius account to connect VTEX Catalog 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 VTEX Catalog with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Product Data Fetching

Need specific item details? You use `get_product` to pull full information on any product, whether you're searching by text or using a known ID. It provides everything the end user needs—price, description, and images—instantly. It’s perfect for showing live data in your UI. When your agent calls `get_sku`, that SKU detail streams directly into React or Next.js without a loading spinner.

Inventory Management via MCP Server

Don't just read the catalog; change it. You manage stock levels by calling `manage_stock` on specific SKUs, updating the available quantity immediately. This is critical for e-commerce checkout flows. If a product needs an update—say, you run out of stock or get a new shipment—your agent handles that logic using `save_product`, letting you create or modify records directly through the MCP Server.

Advanced Catalog Search

Finding things shouldn't be hard. You instruct your AI client to search products by text, brand ID (using `get_brand`), or category ID. The `search_products` tool handles the complexity of filtering results for you. It’s fast and accurate. Whether the user types 'Coca Cola' or provides a precise product code, the system gets back exactly what it needs to continue building the user experience.

Setup guide

Set up VTEX Catalog 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 VTEX Catalog 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 VTEX Catalog 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 VTEX. 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 VTEX Catalog 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 VTEX Catalog MCP in Vercel AI SDK

You pass search criteria (text, brand ID, or category ID) directly to `search_products`. The results stream back immediately into your client-side UI. You don't wait for a full page refresh; the data just appears.

Yeah, you can. By calling `manage_stock`, your agent updates the available quantity of any SKU. This action happens live and is ideal for building checkout or fulfillment tools.

Absolutely. Use `get_brand` to fetch all the necessary information about a specific brand. The results stream in, letting your frontend build out branded content right away.

The server handles multiple identifiers: product names (text), brand IDs (`b/1234`), and category IDs (`c/5678`). You just pass those strings to the relevant tools.

The server only touches public catalog metadata: brand names, product descriptions, and inventory quantities (SKUs). Your agent client is responsible for handling the session token securely.

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