puppeteer_scroll · Steel Puppeteer MCP: Risk & Policy

WHAT IT DOES

What puppeteer_scroll does on Steel Puppeteer

AI agents invoke puppeteer_scroll to trigger actions in Steel Puppeteer. 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 puppeteer_scroll needs a policy

Scrolling is a browser interaction that executes DOM events and can trigger lazy-loading of content, network requests, and JavaScript callbacks. While not directly destructive or financial, it is an active browser operation that can have side effects depending on page behavior, classifying it as Execute.

From the tool's definition 'Scroll the page to trigger lazy-loading' — performs a browser action (scrolling) that triggers dynamic content loading via JavaScript/DOM events in a real browser environment

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

puppeteer_scroll Rate-limited

puppeteer_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": {
    "puppeteer_scroll": {
      "limits": [
        {
          "counter": "puppeteer_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 Steel Puppeteer, so you can run agents against it safely.

FAQ

Questions about puppeteer_scroll

What does the puppeteer_scroll tool do? +

Scroll the page to trigger lazy-loading. It is categorised as a Execute tool in the Steel Puppeteer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on puppeteer_scroll? +

Register the Steel Puppeteer MCP server in PolicyLayer and add a rule for puppeteer_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 Steel Puppeteer. Nothing to install.

What risk level is puppeteer_scroll? +

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

Can I rate-limit puppeteer_scroll? +

Yes. Add a rate_limit block to the puppeteer_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 puppeteer_scroll completely? +

Set action: deny in the PolicyLayer policy for puppeteer_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 puppeteer_scroll? +

puppeteer_scroll is provided by the Steel Puppeteer MCP server (rdvo/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.