How to Use the CloudCart MCP in Vercel AI SDK

Q: How do I initialize the CloudCart MCP client in my Vercel AI SDK project?

Install @ai-sdk/mcp and ai, then use createMCPClient pointing to your Vinkius URL. Pass the tools directly into streamText and remember to call close when the run finishes.

Q: How does the Vercel AI SDK handle CloudCart authentication?

The SDK uses the authProvider config to pass OAuth tokens. Vinkius manages the secure connection, so your frontend code never exposes raw API keys.

Q: Can the model filter products by category?

It can. The model uses liststorecategories to find the correct ID, then filters the catalog to show only relevant items.

Populate your React frontend with real-time CloudCart store data 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 CloudCart MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live inventory to Vercel AI SDK UI

The `list_store_products` tool pulls your live catalog and feeds it directly into your streaming UI components. Your customers see product details load instantly as the model writes, skipping the annoying blank loading states. By pairing this with `get_product_store_details`, your Vercel AI SDK app renders rich product cards on the fly. You get a snappy, highly responsive shopping interface built entirely on edge functions.

Recover lost revenue with instant cart analysis

The `get_abandoned_carts` tool fetches stalled checkouts so your edge-rendered agent can draft personalized recovery offers instantly. You don't have to wait for heavy batch jobs to run in the background. This MCP Server feeds the raw cart data straight into your Vercel AI SDK stream, letting the model suggest tailored discounts based on what customers left behind. It makes high-converting recovery campaigns dead simple to build.

Read CloudCart orders inside your custom agent UI

The `list_store_orders` tool retrieves recent purchases to power customer support widgets right inside your web app. Your users get immediate, accurate updates without your backend team writing complex API glue code. Combined with `get_order_store_details`, this MCP setup lets your Vercel AI SDK client display itemized receipts and shipping status on demand. It keeps your support pipeline fast and completely transparent.

Setup guide

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

Install `@ai-sdk/mcp` and `ai`, then use `createMCPClient` pointing to your Vinkius URL. Pass the tools directly into `streamText` and remember to call `close` when the run finishes.

Yes. This MCP Server runs on lightweight V8 isolates, making it fast enough to call from any Vercel edge runtime without hitting cold start issues.

The SDK uses the `authProvider` config to pass OAuth tokens. Vinkius manages the secure connection, so your frontend code never exposes raw API keys.

It can. The model uses `list_store_categories` to find the correct ID, then filters the catalog to show only relevant items.

Completely. Vinkius runs this MCP Server in an isolated, zero-trust sandbox that never persists your transaction history or customer contact records.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.