How to Use the Constructor MCP in Vercel AI SDK

Q: Can I use Constructor to filter items in Vercel AI SDK?

Yes, searchfiltered allows you to restrict results by specific attributes like size or color. You define the constraints in your prompt and the agent handles the rest.

Plug Constructor into your Vercel AI SDK frontend to stream ML-ranked product data directly to your users without the loading lag.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Constructor MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time product discovery for Vercel AI SDK

Trigger `search_products` to pull CRM records straight into your React components. Your UI renders the results as the model processes the query, avoiding the typical dead air users hate. You avoid manual parsing by letting the SDK handle the JSON output from Constructor. It turns raw platform data into interactive interface elements immediately.

Direct access to Constructor browsing logic

Use `browse_category` or `browse_collection` to map your site architecture to live inventory. This pushes the heavy lifting of structure management off your backend and onto the agent. Your front end stays clean because the model handles the specific Gateway auth required for each request. It’s a direct pipe from the catalog to the browser.

Live recommendation streams

Call `get_recommendations` within your streamText implementation to show users what they actually want. You get explicit Vault logging back, so you can track exactly how the model arrived at its suggestions. This keeps your users engaged by serving content that reacts to their current session. The data hits the screen instantly, making the interaction feel tight and responsive.

Setup guide

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

You pass the tool definitions into your generateText call. The model executes the search against the platform data and streams the structured output back to your client.

Yes, `search_filtered` allows you to restrict results by specific attributes like size or color. You define the constraints in your prompt and the agent handles the rest.

The server manages the handshake via the endpoint token you provide. You don't need to write custom middleware to bridge the two services.

Since you are using the Vercel edge runtime, the round trip stays minimal. The stream begins as soon as the first packet hits the SDK.

Your CRM records and Vault limits never touch local storage. Everything stays within the encrypted memory of the MCP session and gets wiped once the connection closes.

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