browser_stop_video

What browser_stop_video does on Playwright

AI agents invoke browser_stop_video to trigger actions in Playwright. 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_stop_video is rated High

This tool executes a command to stop video playback in a browser, which is an action with external effects on the browsing session. It doesn't merely read data (Read), create reversible content (Write), or permanently delete data (Destructive). It falls under Execute because it triggers an operation on a web page whose real-world consequences depend on context—stopping a video being streamed, recorded, or monitored.

From the tool's definition Tool is part of a browser automation server (@playwright/mcp) that 'lets LLMs interact with web pages' and 'trigger external operations'. The tool name 'browser_stop_video' indicates it performs an action on web content.

The rule that runs browser_stop_video safely

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

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

Questions about browser_stop_video