run_advisors

What run_advisors does on Mcpg

AI agents invoke run_advisors to trigger actions in Mcpg. 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.

Why run_advisors is rated High

The name 'run_advisors' combined with the PostgreSQL server context strongly indicates execution of advisory functions or diagnostic routines. While these are typically read-only operations (PostgreSQL advisors analyze but don't modify), the 'run' verb indicates active code execution whose effects depend on database state and arguments. This fits Execute rather than Read due to the explicit execution trigger.

From the tool's definition Tool name 'run_advisors' on a PostgreSQL MCP server suggests executing advisory functions. The context of sibling tools (analyze_query_plan, analyze_lock_hotspots, etc.) indicates this tool likely executes database diagnostic/advisory operations.

The rule that runs run_advisors safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcpg, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_advisors, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_advisors": {
      "limits": [
        {
          "counter": "run_advisors_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about run_advisors