How to Use the StarRocks MCP in Mastra AI

Q: Can I use Mastra AI to list tables in StarRocks?

Yes. You can call listtables inside your workflow. This allows you to programmatically discover all available datasets within a specified database before running an analysis job.

Q: What is the best way to get schema details with StarRocks and Mastra AI?

Use gettableschema. You can integrate this into your workflow to ensure that any subsequent query execution has the correct, up-to-date column definitions.

Q: If I need schema details for a table in StarRocks and Mastra AI, which tool should I use?

Use gettableschema. This function provides the metadata necessary to build reliable data pipelines by confirming column names and types before any job runs.

Build resilient, multi-step StarRocks workflows with the Mastra AI agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect StarRocks MCP to Mastra AI

Create your Vinkius account to connect StarRocks to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup StarRocks with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate Complex Data Validation

You can chain multiple steps into a single workflow. For instance, first call `list_databases` to see what exists, then check resource limits using `get_storage_usage`. If the usage is high, the agent automatically pauses and notifies an admin. The Mastra AI framework manages this flow state. It handles retries with exponential backoff if a step fails, letting you build complex processes that don't break when things go wrong.

Monitor Cluster Health Automatically

The agent can monitor the entire physical stack. Use `get_cluster_info` to pull high-level node data, followed by calling `list_nodes` for granular backend status checks. This creates a reliable audit trail. This is perfect for automated deployment hooks where you need confirmation that all necessary services are online before proceeding.

Track Data Loading Jobs

When data gets loaded, you need to know if it worked. The agent can list jobs using `list_jobs` and also check materialized views with `list_mvs`. This lets your workflow confirm ETL completion status. You'll build workflows that automatically wait for a specific job ID to appear in the results before moving on to data analysis.

Setup guide

Set up StarRocks MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All StarRocks tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "starrocks-mcp-client",
  servers: {
    "starrocks-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "StarRocks Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to StarRocks tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent StarRocks transactions"
);
console.log(result.text);

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 StarRocks. 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 StarRocks 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 StarRocks MCP in Mastra AI

The agent framework natively supports automatic retries with exponential backoff. If `execute_query` fails due to a transient network issue, the workflow will try again using increasing wait times.

Yes. You can call `list_tables` inside your workflow. This allows you to programmatically discover all available datasets within a specified database before running an analysis job.

Use `get_table_schema`. You can integrate this into your workflow to ensure that any subsequent query execution has the correct, up-to-date column definitions.

Absolutely. The framework allows you to define dependencies between tools. For example, it won't attempt `execute_query` until the result from `get_cluster_info` is successfully processed.

Use `get_table_schema`. This function provides the metadata necessary to build reliable data pipelines by confirming column names and types before any job runs.

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