How to Use the eCellar MCP in Vercel AI SDK

Q: How do I handle eCellar authentication inside an MCP Server setup with Vercel AI SDK?

You pass your Vinkius credential token to the createMCPClient transport configuration. The SDK routes all calls securely, ensuring tools like getorder only run when authorized.

Q: Can I stream eCellar wine club lists using the Vercel AI SDK?

Yes, you use listclubmembers combined with streamText to render active members in real-time. This bypasses slow API loading times on your winery's admin dashboard.

Q: Do I need to close the eCellar connection in Vercel AI SDK edge functions?

Yes, always call mcpClient.close() at the end of your execution block. This prevents connection leaks when querying eCellar inventory via listinventory.

Q: How does this MCP Server handle large eCellar order histories?

The listorders tool returns paginated transaction data to keep your edge responses fast. Your Next.js app receives the structured JSON payload and renders line-item totals immediately.

Stream eCellar DTC wine inventory and customer profiles directly into your React frontend 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 eCellar MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream eCellar wine details live to Next.js frontends

Your custom store application uses `get_product` and `list_products` to pull vintage years, pricing, and availability directly from eCellar. Instead of waiting for a full page reload, the Vercel AI SDK streams these live wine details straight into your React components. This setup avoids the typical loading spinner lag. Your application calls `mcpClient.tools()` to grab the product data and feeds it directly into `streamText` so your customers see wine details instantly.

Live tasting reservation checks with Vercel AI SDK

The `list_reservations` tool exposes real-time tasting room availability directly to your client-side application. By hooking this into the Vercel AI SDK, your front-end interface updates booking slots as soon as the eCellar database processes a change. You manage these live reservation updates inside Vercel Edge Functions to keep booking latency low. The connection uses `createMCPClient` to pull the active reservation list, letting guests book tastings without dealing with stale UI states.

Secure customer lookups via this MCP Server

The `get_customer` and `search_customers` tools retrieve VIP profiles and lifetime spend metrics to personalize the shopping experience. By using the Vercel AI SDK on the edge, you fetch this sensitive eCellar customer data only when verified by your session token. Security is handled via the `authProvider` config inside your MCP client initialization. This ensures that only authenticated winery staff can query customer records or view wine club standing during a live chat session.

Setup guide

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

You pass your Vinkius credential token to the `createMCPClient` transport configuration. The SDK routes all calls securely, ensuring tools like `get_order` only run when authorized.

Yes, you use `list_club_members` combined with `streamText` to render active members in real-time. This bypasses slow API loading times on your winery's admin dashboard.

Yes, always call `mcpClient.close()` at the end of your execution block. This prevents connection leaks when querying eCellar inventory via `list_inventory`.

The `list_orders` tool returns paginated transaction data to keep your edge responses fast. Your Next.js app receives the structured JSON payload and renders line-item totals immediately.

All customer PII, wine club status, and order history pulled via `get_customer` remain isolated within Vinkius's secure V8 sandboxes. No data is cached or stored on external servers during the Vercel AI SDK streaming process.

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