AI agents invoke analyze_query to trigger actions in StarRocks MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The description is empty, lowering confidence. However, in StarRocks/SQL contexts, 'ANALYZE' is a DDL/DML statement that collects statistics and can trigger resource-intensive operations on the database engine. Given the sibling tools explicitly cover read and write SQL queries, 'analyze_query' likely executes ANALYZE-type SQL statements or runs query analysis operations — placing it in Execute.
From the tool's definition Tool name 'analyze_query' on a server that 'allows for direct SQL execution'; sibling tools include 'read_query', 'write_query', and 'query_and_plotly_chart' suggesting SQL execution context.
Documented attack patterns abuse exactly the kind of access analyze_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and StarRocks MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for analyze_query:
{
"version": "1",
"default": "deny",
"tools": {
"analyze_query": {
"limits": [
{
"counter": "analyze_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}analyze_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
analyze_query. It is categorised as a Execute tool in the StarRocks MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the StarRocks MCP Server MCP server in PolicyLayer and add a rule for analyze_query: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches StarRocks MCP Server. Nothing to install.
analyze_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the analyze_query rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for analyze_query. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
analyze_query is provided by the StarRocks MCP Server MCP server (starrocks/mcp-server-starrocks). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 StarRocks MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 StarRocks MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.