StarRocks
Interact with StarRocks
Ads
Overview
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. - 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 Co
Installation
uv run --with mcp-server-starrocks mcp-server-starrocks --help
Configuration
{
"mcpServers": {
"mcp-server-starrocks": {
"url": "http://localhost:8000/mcp"
}
}Capabilities
- Run read-only SQL queries
execute `SELECT`, `SHOW`, or `DESCRIBE` statements via `read_query` and optionally save large results to a file.
- Execute DDL/DML commands
run `CREATE`, `INSERT`, `UPDATE`, or `DELETE` operations with `write_query` and get a row-affected confirmation.
- Explore database schemas
list databases, tables, and retrieve `SHOW CREATE TABLE` definitions through `starrocks://` resources.
- Get table and database overviews
use `table_overview` or `db_overview` to fetch column definitions, row counts, and sample rows, with in-memory caching.
- Visualize query results as charts
supply a SQL query and a Plotly expression to `query_and_plotly_chart` and receive a chart image.
- Inspect cluster health and hotspots
identify frequently accessed tables with `top_hot_tables` or low-health tables with `top_bad_tables`, and access internal system metrics via `proc://` resources.
Tags
- database
- sql
- analytics
Related MCP servers
InstantDB
OfficialCreate, manage, and update applications on InstantDB, the modern Firebase.
Jitsu
OfficialManage Jitsu data pipelines from your AI assistant — destinations, streams, connections, syncs, functions, and live events.
PostgreSQL MCP Server
OfficialRun read-only SQL queries and inspect PostgreSQL schemas from your MCP client.
Financial Datasets
OfficialStock market API made for AI agents