How to Use the Lucidworks Fusion (AI Search & Discovery) MCP in Vercel AI SDK

Q: How do I trigger a search query with Lucidworks Fusion (AI Search & Discovery) using Vercel AI SDK?

Import the MCP client and call the lw.querysearch tool within your streamText function. Pass your search string as an argument to get the results back in your stream.

Q: Can I use Lucidworks Fusion (AI Search & Discovery) to filter results in Vercel AI SDK?

Yes. Use the lw.queryfiltered tool to apply specific property constraints. This allows you to narrow down results before they reach your frontend.

Q: Does Lucidworks Fusion (AI Search & Discovery) support Vercel AI SDK document indexing?

It does. You can invoke lw.indexdocuments from your backend routes to add or update records. This works well for syncing user-generated content in real-time.

Q: How do I list query profiles for Lucidworks Fusion (AI Search & Discovery) in Vercel AI SDK?

Call the lw.listqueryprofiles tool. It returns an array of your active profiles, letting you choose the right one for your current search context.

Connect Vercel AI SDK to your search index. Stream semantic results and index documents directly into your frontend UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lucidworks Fusion (AI Search & Discovery) MCP to Vercel AI SDK

Create your Vinkius account to connect Lucidworks Fusion (AI Search & Discovery) 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 Lucidworks Fusion (AI Search & Discovery) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time search results in Vercel AI SDK

Feed your UI live search data by calling `lw.query_search` directly from your edge functions. The results stream into your components without the lag of traditional API round-trips. Your users see search results as they appear. Use `lw.query_filtered` to refine these sets based on specific user input, keeping the interaction snappy and relevant.

Automated document indexing for MCP Server

Push new content to your index using `lw.index_documents` during your build process or on-demand via server actions. This keeps your search data current without manual intervention. Integrate this with your data pipelines to ensure the search index stays synced. It’s a clean way to handle content ingestion while your AI client manages the heavy lifting.

Monitor search health from your dashboard

Track background tasks and index performance using `lw.list_jobs` and `lw.list_collections`. You get visibility into the backend state right inside your monitoring dashboard. Check your active query rules with `lw.list_query_profiles` to verify that your search logic matches current business needs. It's about keeping the search engine transparent and under control.

Setup guide

Set up Lucidworks Fusion (AI Search & Discovery) 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 Lucidworks Fusion (AI Search & Discovery) 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 Lucidworks Fusion (AI Search & Discovery) 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 Lucidworks Fusion. 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 Lucidworks Fusion (AI Search & Discovery) 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 Lucidworks Fusion (AI Search & Discovery) MCP in Vercel AI SDK

Import the MCP client and call the `lw.query_search` tool within your `streamText` function. Pass your search string as an argument to get the results back in your stream.

Yes. Use the `lw.query_filtered` tool to apply specific property constraints. This allows you to narrow down results before they reach your frontend.

It does. You can invoke `lw.index_documents` from your backend routes to add or update records. This works well for syncing user-generated content in real-time.

Call the `lw.list_query_profiles` tool. It returns an array of your active profiles, letting you choose the right one for your current search context.

Your index data remains within your controlled Fusion instance. The MCP connection simply passes the query and document payloads between your client and the server over an encrypted link.

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