How to Use the EZO Asset Intelligence MCP in Vercel AI SDK

Q: How do I connect EZO Asset Intelligence to my Vercel AI SDK project?

Install the packages with npm install ai @ai-sdk/mcp. Use createMCPClient with your Vinkius HTTP URL, pass the tools into streamText, and remember to call mcpClient.close() when the session ends.

Q: What happens when EZO API rate limits are hit during a stream?

The Vercel AI SDK handles the stream error gracefully. If getassetdetaileddata fails due to EZO account limits, the error bubbles up through the stream, allowing your UI to display a clean warning.

Stream real-time EZO Asset Intelligence data directly into your Next.js and React frontend components 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 EZO Asset Intelligence MCP to Vercel AI SDK

Create your Vinkius account to connect EZO Asset Intelligence 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 EZO Asset Intelligence with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time asset availability lists in your AI SDK UI

This integration uses `list_available_assets` and `list_asset_locations` so your Next.js UI can directly query what physical gear is ready to go. Instead of waiting for a backend server to render, your Vercel AI SDK client streams the physical locations of your hardware directly into your frontend components. Users can request a laptop live while the Vercel AI SDK agent verifies physical shelf locations on the fly. You bypass the slow backend API cycles by letting the client-side agent run the queries and update your React state instantly.

Stream overdue checkout lists without loading spinners

The server provides `list_overdue_checkouts` and `list_currently_checked_out_assets` to let your Next.js application track missing gear on the fly. Your Vercel AI SDK application renders these checkout logs as they stream, letting users see exactly who has what equipment. You can set up Edge Functions that execute these EZO queries when a user opens their dashboard. The Vercel AI SDK client runs the tools directly, returning clean JSON that feeds your custom React tables.

Render EZO Asset Intelligence audits in Next.js

This MCP Server exposes `quick_asset_volume_audit` and `list_consumable_inventory` so your Vercel AI SDK agent can pull high-level stock numbers and active counts. The Vercel AI SDK handles the stream, rendering live progress bars as the physical inventory data flows into the browser. You don't need to write custom API endpoints to bridge EZO and your React frontend. The MCP client executes the audit tool, reads the stock levels, and dumps the raw EZO data straight into your UI state.

Setup guide

Set up EZO Asset Intelligence 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 EZO Asset Intelligence 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 EZO Asset Intelligence 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 EZO Asset Intelligence. 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 EZO Asset Intelligence 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 EZO Asset Intelligence MCP in Vercel AI SDK

Install the packages with `npm install ai @ai-sdk/mcp`. Use `createMCPClient` with your Vinkius HTTP URL, pass the tools into `streamText`, and remember to call `mcpClient.close()` when the session ends.

Yes. The Vercel AI SDK is built for edge environments, and because Vinkius hosts the EZO MCP Server in a lightweight sandbox, your edge routes can execute tools like `list_managed_assets` without cold-start penalties.

You can intercept the tool call in your Vercel AI SDK code before it executes. For sensitive actions like checking `list_account_members`, your frontend can show a confirmation button before sending the execution command.

The Vercel AI SDK handles the stream error gracefully. If `get_asset_detailed_data` fails due to EZO account limits, the error bubbles up through the stream, allowing your UI to display a clean warning.

Vinkius runs the server in an ephemeral V8 Isolate sandbox, meaning your EZO API keys are never exposed to the browser. Your Next.js frontend only talks to the secure Vinkius MCP endpoint, keeping your physical inventory records and member lists safe from public exposure.

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