How to Use the Vald MCP in Vercel AI SDK

Q: How do I perform a search using Vald and Vercel AI SDK?

Call searchvectors, passing your query vector as a JSON array of floats. The results then stream into the UI via your AI client, letting users see the match happen in real time.

Q: Can I delete data from Vald using Vercel AI SDK?

Yes, you can permanently remove a vector using deletevector. Just remember this action is irreversible. Be sure your agent client logic handles that final confirmation step.

Q: If I need to check the status of the Vald MCP Server with Vercel AI SDK?

You use getengineinfo to retrieve operational information and health metrics. This confirms that the backend database connection is live before your agent client tries to run a query.

See your AI work live in the UI with Vald and 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 Vald MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Vector Search for Your Client

Run a nearest neighbor vector similarity search using `search_vectors` to find relevant context. Because you're building user-facing products, the results from this MCP Server stream directly into your UI. You won't have that loading spinner delay; the data just appears live.

Managing Vector Data in Client Apps

Need to update what an agent knows? Use `update_vector` by providing the existing ID and the new vector array. This is critical when your AI client needs to incorporate fresh information based on user interaction. It keeps the context accurate, right in the frontend.

Inspecting Vector Health with the MCP Server

Check how Vald is running by calling `get_engine_info`. This tells you operational details and the overall health of the database engine. Similarly, if you need to inspect a specific data point, `get_vector_details` pulls the raw vector data for an ID.

Setup guide

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

Call `search_vectors`, passing your query vector as a JSON array of floats. The results then stream into the UI via your AI client, letting users see the match happen in real time.

Yes, you can permanently remove a vector using `delete_vector`. Just remember this action is irreversible. Be sure your agent client logic handles that final confirmation step.

The MCP Server manages dense vectors, which you pass as JSON arrays of floats for search and insertion. The specific vector data type is what's being handled.

Absolutely. Since the Vercel AI SDK focuses on streaming responses, connecting it to Vald allows you to surface vector search results directly into the user interface as they appear.

You use `get_engine_info` to retrieve operational information and health metrics. This confirms that the backend database connection is live before your agent client tries to run a query.

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