How to Use the OceanBase MCP in Vercel AI SDK

Q: How do I stream OceanBase cluster telemetry using the Vercel AI SDK?

Call mcpClient.tools() and pass the output directly to the streamText function. This sends live metrics from tools like getclusterdetails to your React components as they resolve. Remember to close the client with mcpClient.close() once the stream finishes.

Q: How does the Vercel AI SDK handle long-running OceanBase diagnostics?

It uses partial tool calls to update the UI while getresourcestats pulls large telemetry sets. Your users see the diagnostic progress in real time instead of staring at a frozen screen.

Q: Do I need to write custom UI components for OceanBase data?

No, you can map the JSON outputs from listdatabases directly to your existing React or Vue primitives. The SDK handles the serialization, leaving you to style the database properties however you prefer.

Build live-streaming database administration consoles using Vercel AI SDK to display active OceanBase cluster metrics in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect OceanBase MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream OceanBase Cluster Metrics to UI with Vercel AI SDK

`list_clusters` lets your Vercel AI SDK app pull live cluster layouts directly into edge-rendered React components using the MCP Server. You don't make your users wait for a full page reload or heavy API payloads when checking database health. Once the cluster list is active, `get_cluster_details` streams the exact hardware and node allocation metrics right into the client interface. This setup cuts out loading spinners entirely by piping raw JSON properties straight to the browser.

Real-time Tenant and Resource Monitoring

`get_resource_stats` sends live CPU and memory telemetry from your OceanBase instances straight to your AI client. Your Next.js edge functions process these raw numbers immediately to show instant performance graphs. When tenants start acting up, `list_tenants` identifies the noisy neighbors before they crash your production environment. The streaming setup ensures your SREs see active tenant shifts as they happen.

Dynamic Database Discovery

`list_databases` exposes every schema inside your active tenant to the streaming model context via MCP. Your developer console can render interactive database lists without complex backend query routing. Coupling this tool with `get_tenant_details` allows your frontend to display live storage limits and connection details on the fly. It makes building custom database management dashboards fast and responsive.

Setup guide

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

Call `mcpClient.tools()` and pass the output directly to the `streamText` function. This sends live metrics from tools like `get_cluster_details` to your React components as they resolve. Remember to close the client with `mcpClient.close()` once the stream finishes.

Yes. The Vercel AI SDK is built to execute within edge runtimes, meaning you can run tools like `list_instances` without cold-start delays. You just need to instantiate the HTTP transport pointing to your Vinkius endpoint.

It uses partial tool calls to update the UI while `get_resource_stats` pulls large telemetry sets. Your users see the diagnostic progress in real time instead of staring at a frozen screen.

No, you can map the JSON outputs from `list_databases` directly to your existing React or Vue primitives. The SDK handles the serialization, leaving you to style the database properties however you prefer.

Vinkius manages your cluster credentials in a secure sandbox, preventing raw connection strings from ever reaching the client browser. Your edge functions only receive the sanitized JSON outputs from tools like `get_tenant_details` over encrypted HTTPS channels.

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