browser_performance_audit

What browser_performance_audit does on Looking Glass

AI agents invoke browser_performance_audit to trigger actions in Looking Glass. 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 browser_performance_audit is rated High

This tool likely executes browser performance measurement/auditing logic rather than merely reading static data. Even though the description is empty, the naming pattern and server context (AI-native browser for agents) indicate it runs audit operations. Performance audits can have side effects like triggering network requests, measuring resource consumption, or logging telemetry.

From the tool's definition Tool name 'browser_performance_audit' suggests execution of a performance audit operation in a browser context. Sibling tools like 'browser_click', 'browser_close', and 'browser_analyze_page' demonstrate this server performs browser automation and control.

The rule that runs browser_performance_audit safely

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

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

Questions about browser_performance_audit