How to Use the DBeaver (CloudBeaver) MCP in Vercel AI SDK

Q: How do I initiate a DBeaver (CloudBeaver) connection using Vercel AI SDK?

Install @ai-sdk/mcp and set up the HTTP transport pointing to your Vinkius endpoint. Pass the tools from createMCPClient directly into streamText to let your agent manage connections.

Q: Can I handle user authentication for DBeaver (CloudBeaver) within a Vercel AI SDK app?

Yes. Use the authlogin tool to authenticate sessions using local or SAML providers returned by getauthproviders. The agent processes credentials and maintains the authenticated session state automatically.

Q: How does Vercel AI SDK handle long-running exports from DBeaver (CloudBeaver)?

The agent calls datatransferexportdatafromcontainer to start an asynchronous export task. It then monitors the task status, streaming updates directly to the client UI until the file is ready.

Q: How do I manage database drivers using this MCP server?

Your agent invokes getdriverlist to inspect active drivers on the server. This lets your application display supported database engines to users before they attempt to configure new connections.

Build Next.js database admin tools that stream DBeaver (CloudBeaver) connection updates and exports straight to your Vercel AI SDK client using this 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 DBeaver (CloudBeaver) MCP to Vercel AI SDK

Create your Vinkius account to connect DBeaver (CloudBeaver) 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 DBeaver (CloudBeaver) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Kill Stuck Queries Live with Vercel AI SDK

The `db_sm_terminate` tool gives your Vercel AI SDK frontend immediate control over runaway database sessions on your DBeaver (CloudBeaver) server. When your agent spots a blocked session, it executes the termination call and streams the status change directly to your React components. You don't wait for a full page refresh or poll a backend endpoint. The application uses Edge Functions to shut down dead connections instantly, keeping your DBeaver (CloudBeaver) instance responsive without manual admin intervention.

Stream Export Formats via Vercel AI SDK MCP Server

The `data_transfer_available_stream_processors` tool fetches supported formats like CSV or XLSX, while `data_transfer_export_data_from_results` triggers the actual extraction from your DBeaver (CloudBeaver) server. Your user sees the export progress update in real-time as the Vercel AI SDK streams the task status. This setup avoids blocking the main thread during heavy data operations. The agent coordinates the export from your CloudBeaver instance and delivers the download link the moment the file generation finishes.

Grant Connection Access in Real-Time

The `add_connections_access` tool lets your Vercel AI SDK agent modify access rules for specific teams on your DBeaver (CloudBeaver) server. Your application handles the request on the edge, updating permissions without requiring a slow round-trip. Users request access to a database connection, and the agent processes the change immediately. The Next.js UI updates the team status instantly, showing active access privileges without manual UI refreshes.

Setup guide

Set up DBeaver (CloudBeaver) 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 DBeaver (CloudBeaver) 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 DBeaver (CloudBeaver) 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 CloudBeaver. 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 DBeaver (CloudBeaver) 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 DBeaver (CloudBeaver) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and set up the HTTP transport pointing to your Vinkius endpoint. Pass the tools from `createMCPClient` directly into `streamText` to let your agent manage connections.

Yes. Use the `auth_login` tool to authenticate sessions using local or SAML providers returned by `get_auth_providers`. The agent processes credentials and maintains the authenticated session state automatically.

The agent calls `data_transfer_export_data_from_container` to start an asynchronous export task. It then monitors the task status, streaming updates directly to the client UI until the file is ready.

Your agent invokes `get_driver_list` to inspect active drivers on the server. This lets your application display supported database engines to users before they attempt to configure new connections.

Absolutely. Your database connection credentials, session tokens, and query metadata never pass through third-party servers. All requests run inside an isolated V8 sandbox on Vinkius, routing directly to your CloudBeaver API endpoint.

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