How to Use the Katana MCP in Vercel AI SDK

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

Install @ai-sdk/mcp and initialize createMCPClient with your HTTP transport URL. Call mcpClient.tools() to grab the Katana MCP Server endpoints and pass them directly to streamText.

Q: Can I build a custom UI for Katana sales orders with Vercel AI SDK?

Yes, you can. When the agent uses createsalesorder, you intercept that tool call in your React code to render a custom confirmation card instead of plain text.

Build live React ERP dashboards with the Katana MCP Server using 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 Katana MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Inventory Data

The `get_inventory_by_variant` and `list_inventory` tools stream live stock levels directly into your Vercel AI SDK frontend. End users watch warehouse counts update in real-time without refreshing the page or waiting for batch requests to finish. Instead of building custom polling logic, you map the MCP Server output to React state. Your Edge Functions handle the API calls while users see actual material availability tick up or down instantly.

Instant Sales Order UI

Calling `create_sales_order` through your chat interface generates a live receipt component the second Katana confirms the write. You pass a customer ID and the AI client handles the rest of the payload construction. We built this to cut out loading spinners entirely. When a sales rep types a request, the `list_customers` and `get_sales_order` endpoints feed data back to the UI in chunks, making the application feel instantaneous.

Vercel AI SDK Manufacturing Visibility

This Vercel AI SDK integration exposes `list_manufacturing_orders` and `list_materials` to your application logic. Production managers query their dashboards and get immediate visual feedback on build statuses. Your Next.js app doesn't need to hold a massive ERP state. The agent pulls exact production data when asked, formatting purchase orders from `list_purchase_orders` straight into your custom Svelte components.

Setup guide

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

Install `@ai-sdk/mcp` and initialize `createMCPClient` with your HTTP transport URL. Call `mcpClient.tools()` to grab the Katana MCP Server endpoints and pass them directly to `streamText`.

Yes. You can run the connection logic in an Edge environment. Just remember to call `mcpClient.close()` when your streaming response finishes.

Yes, you can. When the agent uses `create_sales_order`, you intercept that tool call in your React code to render a custom confirmation card instead of plain text.

The SDK catches the error and surfaces it in the tool result block. Your frontend can then display a fallback message or ask the user for missing customer IDs.

The integration reads PII like shipping addresses and supplier names via `list_customers` and `list_suppliers`. Your Vercel environment dictates where that data lives, while the server itself processes the transaction in a V8 Isolate Sandbox and destroys the memory immediately after execution.

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