run_pgq

What run_pgq does on Mcpg

AI agents invoke run_pgq 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_pgq is rated High

The tool name 'run_pgq' combined with the PostgreSQL server context indicates this tool executes queries against a live database. Query execution is classified as Execute rather than Read because: (1) the absence of a description increases uncertainty about scope—it could permit both SELECT and data-modifying statements, (2) even read-only queries can have side effects in PostgreSQL (e.g., triggering expensive…

From the tool's definition Tool name 'run_pgq' suggests executing queries in PostgreSQL (pgq likely refers to PG query execution). The server is described as 'production-grade PostgreSQL' with tools for analyzing query plans and performance metrics.

The rule that runs run_pgq 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_pgq, this is the rule to start with:

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

Questions about run_pgq