How do I connect my StarRocks cluster to my AI client?

You subscribe to the MCP on Vinkius and enter your FE Host, Port, User, and Password. Once connected, your client can immediately start using the capabilities.

Can I run custom SQL queries?

Yes, the execute_query capability allows your agent to run any arbitrary SQL query against your StarRocks cluster.

Which AI clients are compatible with this MCP?

This MCP works with any compatible client, including Claude, Cursor, and Windsurf.

Can I monitor my backend nodes?

Yes, you can use the list_nodes capability to check the status of your backend nodes.

Does this MCP handle data ingestion monitoring?

Yes, the list_jobs capability allows you to monitor your data load jobs and ingestion performance.

How do I find my StarRocks FE Host and Port?

The FE Host is the IP address or domain of your StarRocks Frontend node. The default HTTP port is 8030. You can verify these in your deployment configuration or by contacting your administrator.

Can I execute DELETE or UPDATE queries through this server?

Yes. Use the execute_query capability. As long as your authenticated user has the necessary permissions in StarRocks, you can execute any valid SQL statement, including DDL and DML operations.

Is it possible to monitor cluster health through the agent?

Yes! Use the get_cluster_info and list_nodes capabilities to retrieve real-time status for all Frontend and Backend nodes, helping you identify offline or overloaded nodes instantly.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect StarRocks to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run SQL and monitor clusters without a terminal.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through StarRocks.

01
List nodes
This capability lists your backend nodes to check their current status.
02
Execute query
Use this to run any SQL query against your StarRocks cluster.
03
Get storage usage
This capability retrieves statistics on how much data you are storing.
04
Get table schema
Get the specific structure and schema for a given table.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through StarRocks.

05
List databases
This capability returns a list of all databases in your cluster.
06
List mvs
Retrieve a list of all materialized views available.
07
List tables
Get a list of all tables within a specific database.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through StarRocks.

08
Get cluster info
This capability provides metadata and status for your frontend nodes.
09
List jobs
Check the status and history of your data load jobs.
10
List views
This capability lists the database views you have created.

Real work

What teams actually run

Schema Auditing

Quickly verify table structures and database schemas using your agent.

Cluster Health Checks

Monitor FE and BE node status to ensure your distributed cluster is running smoothly.

Pipeline Monitoring

Track the performance and status of data load jobs in your analytical pipelines.

Ad-hoc Data Analysis

Run SQL queries to get immediate answers from your data without manual coding.

Automate a task

Put StarRocks to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

StarRocks works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put StarRocks to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

961ms average. Fast in production.

StarRocks is checked daily against the live service.

Daily averagePeak 1242ms

Oct 5Today

Fastest day: 778ms
Slowest day: 1242ms
14-day trend: Slowing+15%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of StarRocks, so you can see the experience inside your AI.

It does not authenticate your account with StarRocks. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

StarRocks Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_bhPoKhzny8myTwStxuxPah44hAT7Sn8O3RSNdBbS/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — StarRocks capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "starrocks-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_bhPoKhzny8myTwStxuxPah44hAT7Sn8O3RSNdBbS/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up StarRocks in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work StarRocks owners hand off.

This MCP is built for technical users managing large scale analytical workloads.

01
Data Engineers
They use the agent to automate schema audits and monitor ingestion pipelines.
02
Analytics Leads
They coordinate data access and audit materialized views through their AI workspace.
03
Infrastructure SREs
They monitor cluster node health and storage usage via a single interface.

FAQ

Questions StarRocks owners ask.

01
How do I connect my StarRocks cluster to my AI client?
You subscribe to the MCP on Vinkius and enter your FE Host, Port, User, and Password. Once connected, your client can immediately start using the capabilities.
02
Can I run custom SQL queries?
Yes, the execute_query capability allows your agent to run any arbitrary SQL query against your StarRocks cluster.
03
Which AI clients are compatible with this MCP?
This MCP works with any compatible client, including Claude, Cursor, and Windsurf.
04
Can I monitor my backend nodes?
Yes, you can use the list_nodes capability to check the status of your backend nodes.
05
Does this MCP handle data ingestion monitoring?
Yes, the list_jobs capability allows you to monitor your data load jobs and ingestion performance.
06
How do I find my StarRocks FE Host and Port?
The FE Host is the IP address or domain of your StarRocks Frontend node. The default HTTP port is 8030. You can verify these in your deployment configuration or by contacting your administrator.
07
Can I execute DELETE or UPDATE queries through this server?
Yes. Use the execute_query capability. As long as your authenticated user has the necessary permissions in StarRocks, you can execute any valid SQL statement, including DDL and DML operations.
08
Is it possible to monitor cluster health through the agent?
Yes! Use the get_cluster_info and list_nodes capabilities to retrieve real-time status for all Frontend and Backend nodes, helping you identify offline or overloaded nodes instantly.

Explore

More in Brain Trust

Connect StarRocks to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

List nodes

Execute query

Get storage usage

Get table schema

05-07

List databases

List mvs

List tables

08-10

Get cluster info

List jobs

List views

What teams actually run

Schema Auditing

Cluster Health Checks

Pipeline Monitoring

Ad-hoc Data Analysis

Building your own app? The connector is yours to use.

StarRocks Connector

Claude Desktop

Data Engineers

Analytics Leads

Infrastructure SREs

How do I connect my StarRocks cluster to my AI client?

Can I run custom SQL queries?

Which AI clients are compatible with this MCP?

Can I monitor my backend nodes?

Does this MCP handle data ingestion monitoring?

How do I find my StarRocks FE Host and Port?

Can I execute DELETE or UPDATE queries through this server?

Is it possible to monitor cluster health through the agent?

QuestDB (Time-Series) AI Connector

Tinybird Data Platform AI Connector

PubNub (Real-time Messaging) AI Connector

Real-Time Currency Exchange AI Connector

Suggestions

Papertrail (Real-time Cloud Log Manager) AI Connector

Data Pipeline Prover AI Connector

Sablier (Token Streaming & Real-time Payroll) AI Connector

data.world AI Connector