How to Use the MyScale (SQL Vector Database API) MCP in Vercel AI SDK

Q: How do I connect MyScale (SQL Vector Database API) to Vercel AI SDK?

Install @ai-sdk/mcp and call createMCPClient using the Vinkius HTTP transport URL. Pass the tools directly into generateText or streamText to let your agent query the database. Always call close() on the client when your session ends.

Q: Can I run custom join queries using MyScale (SQL Vector Database API) and Vercel AI SDK?

Yes. You use executesqlquery to run any standard SQL join between your relational metadata and vector tables. The server formats the response in JSON automatically for your frontend.

Q: How does this MCP Server handle long-running index builds in Vercel AI SDK?

You trigger the build with createvectorindex and monitor it using checkindexstatus. Since edge functions have timeouts, you should run these checks asynchronously or through a background polling loop rather than blocking the main stream.

Q: Do I need a separate database driver to check connection status?

No. The pingcluster tool checks connectivity directly through the MCP. Your agent can run this check before attempting any heavy queries or index builds.

Stream MyScale SQL vector searches directly to your React or Next.js frontend with Vercel AI SDK and our MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MyScale (SQL Vector Database API) MCP to Vercel AI SDK

Create your Vinkius account to connect MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute raw SQL queries inside Vercel AI SDK

The `execute_sql_query` tool lets your agent run SQL statements directly against your cluster. It automatically appends the JSON format so you do not have to parse raw database outputs in your frontend code. This means you get clean, structured data streaming directly to your Next.js components. No intermediate API routes or manual formatting required.

Run vector searches with this MCP Server

The `vector_search` tool runs similarity lookups by auto-generating the underlying SQL query for you. It handles the high-dimensional math and returns matched document IDs and distances. Because it works with the Vercel AI SDK, those search results stream straight to the user interface. Your users see semantic matches populate in real-time instead of staring at a blank loading screen.

Build and monitor indices at the edge

The `create_vector_index` tool builds the MSTG index on your tables to keep search speeds fast. You can track the progress of these heavy operations with `check_index_status` to see if the index is built or still processing. Doing this directly through your edge functions keeps your database maintenance close to your application logic. You do not need to switch back and forth between different administrative tools.

Setup guide

Set up MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) 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 MyScale. 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 MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and call `createMCPClient` using the Vinkius HTTP transport URL. Pass the tools directly into `generateText` or `streamText` to let your agent query the database. Always call `close()` on the client when your session ends.

Yes. You use `execute_sql_query` to run any standard SQL join between your relational metadata and vector tables. The server formats the response in JSON automatically for your frontend.

You trigger the build with `create_vector_index` and monitor it using `check_index_status`. Since edge functions have timeouts, you should run these checks asynchronously or through a background polling loop rather than blocking the main stream.

No. The `ping_cluster` tool checks connectivity directly through the MCP. Your agent can run this check before attempting any heavy queries or index builds.

This MCP Server runs SQL queries inside Vinkius's V8 sandboxed environment. No connection details are exposed to the client-side code, and the ephemeral container wipes all session memory immediately after execution.

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