How to Use the Doofinder MCP in Vercel AI SDK

Q: How does Doofinder stream autocomplete suggestions using the Vercel AI SDK?

The suggest tool fetches predictive terms directly from your Doofinder search engines. The Vercel AI SDK streams these text predictions directly to your React input component as the user types, eliminating the need for complex state management or polling.

Q: Can I paginate large Doofinder search results inside a Vercel AI SDK edge function using this MCP Server?

Yes, you use searchpagination to request specific chunks of your Doofinder product catalog. The Vercel AI SDK handles the asynchronous data chunks on the edge, keeping your serverless functions light and responsive.

Q: How do we handle custom sorting for Doofinder queries in Vercel AI SDK?

You invoke searchsorted to order your Doofinder product results by price, relevance, or creation date. The Vercel AI SDK receives this sorted payload and immediately streams the ordered list to your frontend UI.

Q: What is the best way to clean up the MCP client connection after a Doofinder search?

Always call mcpClient.close() at the end of your execution block. This prevents connection leaks in your serverless environment and ensures resources are freed up instantly.

Get instant Doofinder search results streaming straight to your Next.js UI 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 Doofinder MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Doofinder search results live with Vercel AI SDK

The `search_keyword` tool fetches matched products from Doofinder when a customer types a query into your Vercel AI SDK app. Your Vercel AI SDK application binds this MCP tool directly to the stream, pulling matching Doofinder items instantly without forcing the user to wait for a full page reload. You combine this with `search_pagination` to handle large Doofinder result sets on the fly. The Vercel AI SDK streams the paginated JSON chunks directly to your React components, keeping the interface snappy and reducing the initial page load time to under 100ms.

Render Doofinder auto-suggestions during active typing

The `suggest` tool targets search terms and autocomplete options in Doofinder before the customer even finishes typing their query. This MCP Server feeds these autocomplete payloads directly into your edge-rendered Vercel AI SDK input fields, minimizing keystrokes and getting users to product pages faster. By integrating this Doofinder tool with your edge runtime, you bypass heavy database queries completely. The Vercel AI SDK handles the stream transmission, feeding the autocomplete array directly into your custom search bar component.

Apply instant Doofinder facet filters on the edge

The `search_filtered` tool isolates specific Doofinder product attributes like price, brand, or size directly inside your Vercel AI SDK application. This MCP tool lets your AI client filter down massive Doofinder inventories using precise criteria, returning only the exact SKU matches your customer wants. This approach avoids the typical lag of traditional search clients. The Vercel AI SDK parses the filtered Doofinder payload on the fly, updating your UI state immediately without forcing a full-screen refresh.

Setup guide

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

The `suggest` tool fetches predictive terms directly from your Doofinder search engines. The Vercel AI SDK streams these text predictions directly to your React input component as the user types, eliminating the need for complex state management or polling.

Yes, you use `search_pagination` to request specific chunks of your Doofinder product catalog. The Vercel AI SDK handles the asynchronous data chunks on the edge, keeping your serverless functions light and responsive.

You invoke `search_sorted` to order your Doofinder product results by price, relevance, or creation date. The Vercel AI SDK receives this sorted payload and immediately streams the ordered list to your frontend UI.

Always call `mcpClient.close()` at the end of your execution block. This prevents connection leaks in your serverless environment and ensures resources are freed up instantly.

The server processes your search queries and index metadata inside an isolated V8 sandbox, never caching your catalog schema on external servers. All authentication tokens pass directly to the Gateway without persistent storage.

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