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

Q: How do I search for nearest neighbors using Vertex AI Vector Search with Vercel AI SDK?

You call searchnearestneighbors and provide the endpoint ID, deployed index ID, and a query vector as JSON. The result streams back to your UI in real time when you use the Vercel AI SDK.

Q: If I need to check my project's available indexes, which tool should I use with Vertex AI Vector Search and Vercel AI SDK?

Use listvectorindexes. It lists every single vector index in your Google Cloud project. This is the first stop you want when setting up any new client-side interaction.

Q: Can I monitor long-running operations using Vertex AI Vector Search and Vercel AI SDK?

Yeah, absolutely. The listvectoroperations tool lets you track all the background tasks for vector indexes. This is great for knowing if a major index build job finished or failed.

Q: I'm building a multi-step app; how do I manage endpoint IDs with Vertex AI Vector Search and Vercel AI SDK?

You can use listindexendpoints to get all available index endpoints. Then, you feed that ID into the search function, making sure your client knows exactly where to point.

Stream Vector Search results live into your UI using 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 Vector Search MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and display vectors in real time.

The `search_nearest_neighbors` tool lets you run vector similarity checks against billions of embeddings. When you call this function, the results stream directly into your Next.js component; users see the data appear live instead of waiting for a loading spinner. It's crucial because it keeps your front-end feeling fast and responsive. You can chain this tool result output straight into your `streamText` calls.

Manage index endpoints on the client side.

Need to know what indexes are available? Call `list_index_endpoints`. This pulls all active endpoint IDs, letting you build a dynamic UI that shows users exactly which services your agent can talk to. It's perfect for building dashboards where the user needs visibility into backend resources. Alternatively, use `list_deployed_indexes` to quickly check out what specific indexes are running under an endpoint ID. This gives you granular control over resource availability right in your client application.

Check index status and metadata.

Before making a search query, you need to make sure the index is configured correctly. The `get_index_details` tool pulls all the necessary metadata for any specific vector index. This lets your client code validate settings before attempting a costly operation. You can also use `list_vector_indexes` or `list_vector_operations` to get a full overview of every single vector index and long-running job in the project, keeping your entire system visible from one place.

Setup guide

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

You call `search_nearest_neighbors` and provide the endpoint ID, deployed index ID, and a query vector as JSON. The result streams back to your UI in real time when you use the Vercel AI SDK.

Use `list_vector_indexes`. It lists every single vector index in your Google Cloud project. This is the first stop you want when setting up any new client-side interaction.

Yeah, absolutely. The `list_vector_operations` tool lets you track all the background tasks for vector indexes. This is great for knowing if a major index build job finished or failed.

This server touches Vector Index metadata and configuration details. It manages the operational status of your embeddings without exposing raw search query vectors or user text data directly.

You can use `list_index_endpoints` to get all available index endpoints. Then, you feed that ID into the search function, making sure your client knows exactly where to point.

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