mcp-server-starrocks
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_queryA | Execute a SELECT query or commands that return a ResultSet. Set output_file to write the full result to disk instead of returning it inline (useful for large results).. Use set_session_db to set a per-session default database |
| write_queryB | Execute a DDL/DML or other StarRocks command that do not have a ResultSet. Use set_session_db to set a per-session default database |
| analyze_slow_queries_topnC | Analyze top N slowest queries and identify performance bottlenecks |
| analyze_queryC | Analyze a query and get analyze result using query profile. Use set_session_db to set a per-session default database |
| collect_query_dump_and_profileB | Run a query to get it's query dump and profile, output very large, need special tools to do further processing |
| top_hot_tablesC | Get top hot tables by audit-log visit count |
| top_bad_tablesB | Get top bad tables by table health score |
| query_and_plotly_chartC | using sql |
| table_overviewA | Get an overview of a specific table: columns, sample rows (up to 3), and total row count. Uses cache unless refresh=true. Use set_session_db to set a per-session default database |
| db_summaryA | Quickly get summary of a database with tables' schema and size information. Use set_session_db to set a per-session default database |
| set_session_dbA | Set or clear the default database for THIS MCP session. Subsequent tool calls without an explicit |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| All Databases | List all databases in StarRocks |
TDQS
Scored across 11 tools
Tools generally have distinct targets: read_query for SELECT, write_query for DDL/DML, profiling/analysis tools for diagnostics, and overview tools for schema/table information. The main potential confusion is between analyze_query and collect_query_dump_and_profile, but their descriptions indicate different collection vs. analysis purposes.
All names use snake_case and many follow a verb_noun pattern like write_query, read_query, and analyze_query. However, tools like table_overview, db_summary, top_hot_tables, and query_and_plotly_chart break that pattern, making the overall convention mixed though still readable.
11 tools is well-scoped for a StarRocks database and query-analysis server. Each tool covers a distinct capability and the count is neither too small to be useful nor too large to be overwhelming.
The set covers query execution, schema/table overviews, performance analysis, query profiling, and session database management. An explicit list_databases/list_tables tool is missing, but db_summary and table_overview largely compensate for that gap.