screencast_start · Chrome Devtools MCP: Risk & Policy

WHAT IT DOES

What screencast_start does on Chrome Devtools

AI agents invoke screencast_start to trigger actions in Chrome Devtools. 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 screencast_start needs a policy

This tool triggers an external operation (screen recording) in a live browser. It initiates an ongoing process that captures browser activity, which is an execution/operational action rather than a simple read. While it reads visual data, it also starts a recording process with side effects (resource consumption, potential privacy implications of capturing screen content).

From the tool's definition Starts recording a screencast (video) of the selected page in mp4 format

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screencast_start Rate-limited

screencast_start 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": {
    "screencast_start": {
      "limits": [
        {
          "counter": "screencast_start_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 Chrome Devtools, so you can run agents against it safely.

FAQ

Questions about screencast_start

What does the screencast_start tool do? +

Starts recording a screencast (video) of the selected page in mp4 format. It is categorised as a Execute tool in the Chrome Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on screencast_start? +

Register the Chrome Devtools MCP server in PolicyLayer and add a rule for screencast_start: 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 Chrome Devtools. Nothing to install.

What risk level is screencast_start? +

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

Can I rate-limit screencast_start? +

Yes. Add a rate_limit block to the screencast_start 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 screencast_start completely? +

Set action: deny in the PolicyLayer policy for screencast_start. 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 screencast_start? +

screencast_start is provided by the Chrome Devtools MCP server (shivamprasad99/chrome-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.