Happy slice of mcp pizzaMCP.pizza

mcp-server-starrocks

MCP.Pizza Chef: StarRocks

Ask a question in plain English and this StarRocks connector writes the query, runs it against your cluster, and hands back the rows or a chart drawn straight from the results. Ten tools cover reading, writing, table and database summaries, query analysis, and spotting your busiest or least healthy tables. It signs in with your StarRocks username and password, not a separate key. There is no read-only mode, so the write tool will run DROP or DELETE without asking. The whole-database overview named in the documentation is commented out in the code and never loads.

Coding
Data

Use This MCP server To

Ask for last month's revenue without writing a query Chart daily signups straight from the database Get a plain summary of what a table contains Find out which tables my team queries most often Spot tables with health problems before they cause trouble Understand why one slow query is holding things up

README

MseeP.ai Security Assessment Badge

StarRocks Official MCP Server

The StarRocks MCP Server acts as a bridge between AI assistants and StarRocks databases. It allows for direct SQL execution, database exploration, data visualization via charts, and retrieving detailed schema/data overviews without requiring complex client-side setup.

StarRocks Server MCP server

Features

  • Direct SQL Execution: Run SELECT queries (read_query) and DDL/DML commands (write_query).
  • Database Exploration: List databases and tables, retrieve table schemas (starrocks:// resources).
  • System Information: Access internal StarRocks metrics and states via the proc:// resource path.
  • Detailed Overviews: Get comprehensive summaries of tables (table_overview) or entire databases (db_overview), including column definitions, row counts, and sample data.
  • Data Visualization: Execute a query and generate a Plotly chart directly from the results (query_and_plotly_chart).
  • Intelligent Caching: Table and database overviews are cached in memory to speed up repeated requests. Cache can be bypassed when needed.
  • Flexible Configuration: Set connection details and behavior via environment variables.

Prerequisites

  • Python 3.11 or newer.
  • A reachable StarRocks cluster (FE service). By default the server connects to localhost:9030 over the MySQL protocol.
  • uv — a fast Python package and project manager (a modern replacement for pip + virtualenv) from Astral. This project uses uv to resolve dependencies, create the virtual environment, and launch the server. The uv run commands throughout this README automatically create an isolated environment and install the required dependencies on first use, so no manual pip install step is needed.

Installing uv

# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

# Or via Homebrew / pipx / pip
brew install uv
# pipx install uv
# pip install uv

mcp-server-starrocks FAQ

Do I need a paid key to use it?
No. You give it a StarRocks database username and password, or a connection string containing them. On a Mac it can also pull the password out of your Keychain instead of a config file.
Can it change or delete my data?
Yes, and there is no read-only switch. The write tool runs whatever it is handed, including DROP TABLE and DELETE, with no confirmation step. Point it at a limited database account if that worries you.
Can I use this to build a chart from my data?
Yes — one tool runs your query and draws a chart from the result, which it can save to a file or hand back for display.
Can it summarize an entire database at once?
Not the way the README implies. The full per-table overview tool is commented out in the source and never registers. A lighter summary tool still returns table names, columns, and sizes.
Which apps does it work in?
Any MCP app that can launch a local command or reach a local web address. Claude Desktop is the documented example, and it can also run as a background service on a port you choose.
How hard is it to set up?
This one is for technical users. You need Python 3.11 or newer, the uv tool installed, and a StarRocks cluster you can already reach.
Is this an official project?
Yes. It is maintained by StarRocks in their own GitHub organization and was last updated in mid-2026.