vision.run_perceptual_critics

What vision.run_perceptual_critics does on Visionmcp

AI agents invoke vision.run_perceptual_critics to trigger actions in Visionmcp. 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 vision.run_perceptual_critics is rated High

This tool triggers execution of specialist critic processes whose effects depend on the input (which critics run, what data they analyze). While framed as analytical/verification work, it executes code/logic that transforms data and produces sealed findings. It's not merely a Read operation (which would be passive query/retrieval) because 'run' and 'seal' indicate active operations with side effects.

From the tool's definition Tool name 'run_perceptual_critics' uses the verb 'run', which indicates execution of external operations. The description 'Run specialist critics and seal a PerceptualCritique' confirms it executes specialist critic processes and produces measurable findings…

The rule that runs vision.run_perceptual_critics safely

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

{
  "version": "1",
  "default": "deny",
  "tools": {
    "vision.run_perceptual_critics": {
      "limits": [
        {
          "counter": "vision.run_perceptual_critics_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about vision.run_perceptual_critics