How to Use the Vertex AI Search MCP in Vercel AI SDK

Q: How do I perform a semantic search with Vertex AI Search and Vercel AI SDK?

You call searchdocuments by passing the data store ID and the user's query text. Because you're using the Vercel AI SDK, the results stream back to your UI in real-time, so there’s no waiting for a single page load.

Q: Can I list all my available data sources with Vertex AI Search and Vercel AI SDK?

Yup. Use listdatastores to get the full collection of sources configured in your account. This is how you ensure your application knows which knowledge base to query.

Q: What data types can I use for recommendations with Vertex AI Search and Vercel AI SDK?

The getrecommendations tool requires a data store ID and user event information formatted as a JSON object. You'll send this structured data alongside the request.

Q: Does the MCP Server handle document indexing status for Vercel AI Search and Vercel AI SDK?

Yes, listdatastoredocuments lets you check exactly which documents are indexed within a specific data store branch. You can verify your content is ready before calling any search tools.

Get real-time, grounded answers in your Next.js app 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 Vertex AI Search MCP to Vercel AI SDK

Create your Vinkius account to connect Vertex AI Search 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 Vertex AI Search with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Grounding Answers on Private Data

Use `get_grounded_answer` to pull a natural language answer straight from a data store's documents. This is perfect for building FAQs or knowledge bases where the user needs definitive, source-backed answers. It makes your application smarter because it doesn't just guess; it references specific parts of your private corporate documentation.

Personalized User Recommendations

The `get_recommendations` tool takes a data store ID and a JSON object containing user events. This lets you display relevant items or links based on what the user just looked at, right in your React component. It’s great for e-commerce sites or content platforms that need to guide users using their unique activity history.

Structured Data Discovery

Need to know what data you've indexed? `list_data_stores` gives you a list of all available search sources. You can pair this with `search_documents`, which runs the actual query against documents in any specific store. This lets your front end dynamically build complex search forms that target multiple, separate parts of your backend data.

Setup guide

Set up Vertex AI Search 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 Vertex AI Search 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 Vertex AI Search 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 Vertex AI Search. 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 Vertex AI Search 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 Vertex AI Search MCP in Vercel AI SDK

You call `search_documents` by passing the data store ID and the user's query text. Because you're using the Vercel AI SDK, the results stream back to your UI in real-time, so there’s no waiting for a single page load.

Yup. Use `list_data_stores` to get the full collection of sources configured in your account. This is how you ensure your application knows which knowledge base to query.

The `get_recommendations` tool requires a data store ID and user event information formatted as a JSON object. You'll send this structured data alongside the request.

Yes, `list_datastore_documents` lets you check exactly which documents are indexed within a specific data store branch. You can verify your content is ready before calling any search tools.

This server works with private corporate documents and user event metadata. You're dealing with sensitive textual content that must remain grounded and restricted to your defined data stores.

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