How to Use the Marqo AI (Vector Search & Embeddings) MCP in Vercel AI SDK

Q: How does Marqo AI (Vector Search & Embeddings) handle streaming with the Vercel AI SDK?

The server executes tensorsearch and returns raw JSON matches directly to your agent. From there, the Vercel AI SDK streams the text chunks straight to your frontend UI. Users see search results render in real-time instead of staring at a blank loading screen.

Q: How do I index new data using Marqo AI (Vector Search & Embeddings) and Vercel AI SDK?

Your agent invokes adddocuments to push new JSON objects into your index. You can trigger this action directly from a user message or an automated background process in your Next.js application.

Q: How does deletedocuments work when my UI needs to update?

The agent calls deletedocuments with specific IDs to purge outdated records. Your frontend updates instantly as the next search query reflects the deleted items.

Pipe raw semantic search results directly into your Next.js UI using the Vercel AI SDK without waiting for slow API loaders.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marqo AI (Vector Search & Embeddings) MCP to Vercel AI SDK

Create your Vinkius account to connect Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Instantly query vector indices on the edge

The `tensor_search` tool lets your agent run natural language queries directly against your Marqo vector database. By hooking this into your Vercel AI SDK setup, you bypass standard backend bottlenecks. Your edge functions fetch high-dimensional vector matches and push them to the browser immediately. This means you do not have to build custom API endpoints just to query your collection. The agent handles the query, formats the output, and feeds it into your UI stream. It cuts latency and keeps the user interface responsive.

Real-time index status streaming for developers

The `get_index_stats` tool checks index health before your application pushes new document sets. This MCP Server lets your AI client pull document counts and index configurations on demand. Your application can render these metrics live in a developer dashboard. Knowing the exact state of your vector storage prevents indexing failures during high-traffic periods. Instead of guessing, your agent reads the live stats and adjusts its ingestion speed. It is a straightforward way to keep your production search stable.

Dynamic index creation via Vercel AI SDK MCP Server

Spin up isolated vector spaces on the fly using the `create_index` tool over an MCP connection. This capability lets your application build dedicated search partitions for individual users or projects dynamically. You do not need to manually configure indexes in a separate console. Combined with `list_indexes`, your agent checks what exists before running new operations. This prevents naming collisions and keeps your storage organized. It gives your application total programmatic control over its search architecture.

Setup guide

Set up Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI. 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) MCP in Vercel AI SDK

The server executes `tensor_search` and returns raw JSON matches directly to your agent. From there, the Vercel AI SDK streams the text chunks straight to your frontend UI. Users see search results render in real-time instead of staring at a blank loading screen.

Yes. This MCP Server runs in a sandboxed V8 isolate, making it compatible with lightweight edge runtimes. You just initialize the client inside your edge route and pass the tools directly to your generation function.

Your agent invokes `add_documents` to push new JSON objects into your index. You can trigger this action directly from a user message or an automated background process in your Next.js application.

The agent calls `delete_documents` with specific IDs to purge outdated records. Your frontend updates instantly as the next search query reflects the deleted items.

All data stays within your self-hosted or managed Marqo instance. The Vinkius MCP Server acts as an ephemeral proxy, passing your credentials and payload securely without storing your search queries or index files.

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