How to Use the MarketMan MCP in Vercel AI SDK

Build live restaurant dashboards with Vercel AI SDK. Stream inventory counts and food costs directly into your Next.js frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MarketMan MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream stock checks to the UI

The `list_inventory` tool pulls current stock levels for your Vercel AI SDK application. When a line cook asks the chat interface if you are low on anything, the agent hits this endpoint and pipes the exact counts back. You do not wait for a loading spinner. The numbers render on the screen the millisecond the server returns them. Pair this with `list_categories` to build dynamic sorting in your React frontend. If someone selects the dairy category, the UI updates instantly with milk and butter totals. It keeps kitchen staff moving instead of staring at a blank screen waiting for an API resolution.

MarketMan MCP Server cost tracking

The `get_waste_events` tool fetches logged spoilage and spills straight from your database. Your Vercel AI SDK agent reads these records to calculate immediate margin hits. It pushes the financial damage directly to a dashboard component. You can cross-reference those losses using `list_recipes`. The client pulls the exact ingredient costs for a dropped batch of sauce and calculates the real dollar value of the waste. Shift managers see the exact cost of mistakes as they happen.

Render purchase orders instantly

The `list_purchase_orders` tool retrieves recent supplier orders for immediate display. Your application uses this to show managers exactly what is coming off the truck tomorrow. Combine it with `list_vendors` to build a live contact sheet for late deliveries. If an order is missing, the AI grabs the vendor phone number and renders a call button right in the chat interface. You skip the back-office filing cabinet entirely.

Setup guide

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

Install @ai-sdk/mcp in your project. Initialize it with createMCPClient using your endpoint URL. Pass the exposed tools into streamText to pipe the data to your frontend.

Yes. The client handles the streaming HTTP transport natively. When the agent checks stock levels, the text chunks arrive in the UI immediately.

Edge functions have strict execution limits. You should configure your timeout settings to close the mcpClient gracefully if the inventory query stalls.

The agent reads the vendor IDs first. It then passes those parameters into the purchase order tool to return only the relevant deliveries for that supplier.

Only if you build it that way. The server reads raw ingredient pricing via the recipes endpoint. You control the authentication layer in your Vercel application to ensure only logged-in managers can see those financial metrics.

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