browser_start_video_recording · Browser MCP: Risk & Policy

WHAT IT DOES

What browser_start_video_recording does on Browser

AI agents invoke browser_start_video_recording to trigger actions in Browser. 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 IT NEEDS A POLICY

Why browser_start_video_recording needs a policy

This tool triggers an external operation (video recording) whose effects persist and depend on runtime context (what the browser displays during recording). While not destructive or financial, it executes a command that changes system state and initiates background processes.

From the tool's definition Tool name is 'browser_start_video_recording' and description states 'Start recording browser session as video'. This initiates a recording operation with external side effects (creating a video file of browser activity).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_start_video_recording Rate-limited

browser_start_video_recording stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Browser, so you can run agents against it safely.

FAQ

Questions about browser_start_video_recording

What does the browser_start_video_recording tool do? +

Start recording browser session as video (see browser_docs). It is categorised as a Execute tool in the Browser MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_start_video_recording? +

Register the Browser MCP server in PolicyLayer and add a rule for browser_start_video_recording: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Browser. Nothing to install.

What risk level is browser_start_video_recording? +

browser_start_video_recording is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit browser_start_video_recording? +

Yes. Add a rate_limit block to the browser_start_video_recording rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block browser_start_video_recording completely? +

Set action: deny in the PolicyLayer policy for browser_start_video_recording. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides browser_start_video_recording? +

browser_start_video_recording is provided by the Browser MCP server (ricardodeazambuja/browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.