How to Use the CartonCloud MCP in Vercel AI SDK

Q: How do I connect CartonCloud to the Vercel AI SDK?

Install the @ai-sdk/mcp package and initialize it with createMCPClient. Pass the Vinkius endpoint URL using the HTTP transport option. Your Next.js app can then map the returned tools directly into your generation functions.

Connect CartonCloud to the Vercel AI SDK and stream live warehouse data directly into your React or Next.js frontends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CartonCloud MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream CartonCloud MCP Server Data Live

Your frontend users hate loading spinners when checking their logistics data. Calling `get_product_stock` through the Vercel AI SDK pushes stock quantities straight to your React UI as the model receives them. Vinkius hosts the endpoint so you avoid writing custom middleware for warehouse polling. Passing the client into `streamText` exposes logistics endpoints directly to the language model. A prompt asking for transport details triggers `list_consignments` in the background, rendering the shipment statuses instantly on the client side. Close the connection with `mcpClient.close()` when the component unmounts.

Build Customer-Facing Logistics Portals

Giving end users visibility into their shipments requires pulling specific records fast. The `get_sale_order_details` tool fetches exact order data that your Next.js application can render instantly using React Server Components. Edge Functions handle the routing without bogging down your main server. Querying `list_logistics_customers` lets you populate dropdowns dynamically based on tenant data. Your agent client fetches the list and builds the UI components in real-time. You skip the tedious API integration phase and jump straight to building the actual user experience.

Render Invoices and Purchase Orders

Financial data needs accurate representation in your web applications. Fetching records via `list_logistics_invoices` allows your application to build live billing dashboards. The Vercel AI SDK handles the tool calling loop while Vinkius manages the underlying MCP infrastructure. Tracking inbound freight works the same way. The `list_purchase_orders` tool grabs incoming supplier shipments so your frontend can display warehouse receiving schedules. You get raw logistics data piped straight into your Vue or Svelte components.

Setup guide

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

Install the `@ai-sdk/mcp` package and initialize it with `createMCPClient`. Pass the Vinkius endpoint URL using the HTTP transport option. Your Next.js app can then map the returned tools directly into your generation functions.

Yes. The framework natively supports streaming tool results. When the model invokes the stock checking tool, the quantity data appears in your UI immediately instead of waiting for the full response to finish.

Not if you use this MCP Server. Vinkius handles the backend execution inside an isolated sandbox. You just call `list_sale_orders` from your frontend code and let the framework manage the state.

You provide your Vinkius endpoint token when configuring the HTTP transport. The server manages the actual credentials securely. Your client code never touches the raw API keys.

We isolate every request inside an ephemeral V8 sandbox. When your app reads inbound freight records via `list_purchase_orders` or checks active shipments using `list_consignments`, the container destroys itself immediately after returning the payload. No residual data survives the transaction.

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