random_scroll · Puppeteer Real Browser MCP: Risk & Policy

WHAT IT DOES

What random_scroll does on Puppeteer Real Browser

AI agents invoke random_scroll to trigger actions in Puppeteer Real 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 random_scroll needs a policy

This tool executes browser actions (scroll events) in a real browser context. While scrolling itself has minimal blast radius, it is a browser execution action that interacts with live web pages, potentially triggering lazy-loaded content, infinite scroll, or other page-side effects. Classified as Execute because it actively drives browser behavior rather than merely reading state.

From the tool's definition 'Perform random scrolling with natural timing' — triggers browser actions (scrolling) in an active browser session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

random_scroll Rate-limited

random_scroll 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": {
    "random_scroll": {
      "limits": [
        {
          "counter": "random_scroll_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 Puppeteer Real Browser, so you can run agents against it safely.

FAQ

Questions about random_scroll

What does the random_scroll tool do? +

Perform random scrolling with natural timing. It is categorised as a Execute tool in the Puppeteer Real 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 random_scroll? +

Register the Puppeteer Real Browser MCP server in PolicyLayer and add a rule for random_scroll: 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 Puppeteer Real Browser. Nothing to install.

What risk level is random_scroll? +

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

Can I rate-limit random_scroll? +

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

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

random_scroll is provided by the Puppeteer Real Browser MCP server (puppeteer-real-browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.