How to Use the NCR Voyix MCP in Vercel AI SDK

Q: How do I handle NCR Voyix authentication within a Vercel AI SDK app?

You configure the authProvider in the Vercel AI SDK setup to manage OAuth tokens for your retail locations. Vinkius secures these credentials in an isolated V8 sandbox for this MCP, so your frontend never exposes raw API keys to the browser.

Q: How do I close the Vercel AI SDK connection to the NCR Voyix server?

Always call mcpClient.close() inside your React useEffect cleanup function or Next.js API exit handler. This prevents dangling SSE connections and ensures your serverless execution environment releases the active session immediately.

Q: Is customer commerce and loyalty data secure when queried via this server?

Your customer records are safe because all requests to listcustomers and getloyaltyprograms route through an ephemeral, zero-trust Vinkius gateway. No retail customer records or loyalty points are stored on disk, keeping your shoppers' personal information strictly inside your secure NCR database.

Feed NCR Voyix retail data straight to your Next.js UI components in real time using 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 NCR Voyix MCP to Vercel AI SDK

Create your Vinkius account to connect NCR Voyix 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 NCR Voyix with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Vercel AI SDK UI Updates for Stock

The `list_inventory` tool lets your Vercel AI SDK client check exact stock counts across your retail locations without making the user wait for a full page refresh. Because this MCP Server hooks directly into your edge routes, the stock numbers stream straight into your React components the millisecond they are pulled. You don't have to build custom loading states or complex polling mechanisms to show store updates. The SDK handles the streaming transport under the hood, rendering live store metrics from `get_site` directly in the user's chat bubble as they ask about local availability.

Direct Catalog Exploration

The `list_products` tool queries your active retail catalog so your Vercel AI SDK client can display item details inside the chat interface. Instead of fetching the entire catalog and hitting payload limits, the model targets specific SKUs on demand. Combining this with `list_catalogs` allows your Next.js application to switch between seasonal menus or regional product lines on the fly. Your users get immediate, accurate catalog data rendered in native UI components rather than slow, static text blocks.

Real-time Order Tracking

The `get_order` tool retrieves live customer purchase records to update your Vercel AI SDK frontend interface instantly. Your application reads the transaction status and displays a visual progress bar to the customer without manual API glue code. By calling `list_orders`, the model summarizes recent purchases for returning customers directly in the chat window. This cuts down on customer support tickets because buyers see their order history loaded on their screen in real time.

Setup guide

Set up NCR Voyix 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 NCR Voyix 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 NCR Voyix 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 NCR Voyix. 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 NCR Voyix 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 NCR Voyix MCP in Vercel AI SDK

You configure the `authProvider` in the Vercel AI SDK setup to manage OAuth tokens for your retail locations. Vinkius secures these credentials in an isolated V8 sandbox for this MCP, so your frontend never exposes raw API keys to the browser.

Yes, because the MCP Server runs on edge-compatible infrastructure to prevent blocking main thread execution. The `list_inventory` tool feeds data directly into `streamText`, which pushes raw stock metrics to your React hooks without UI freezes.

This server packages complex retail endpoints into clean, model-callable tools like `list_sites` and `get_product`. You avoid writing hundreds of lines of routing boilerplate because the SDK reads the tool schemas and invokes them automatically.

Always call `mcpClient.close()` inside your React `useEffect` cleanup function or Next.js API exit handler. This prevents dangling SSE connections and ensures your serverless execution environment releases the active session immediately.

Your customer records are safe because all requests to `list_customers` and `get_loyalty_programs` route through an ephemeral, zero-trust Vinkius gateway. No retail customer records or loyalty points are stored on disk, keeping your shoppers' personal information strictly inside your secure NCR database.

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