screen_scroll · Screen Agent MCP: Risk & Policy

WHAT IT DOES

What screen_scroll does on Screen Agent

AI agents invoke screen_scroll to trigger actions in Screen Agent. 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 screen_scroll needs a policy

This tool performs a scroll action on the desktop UI, which is an external operation interacting with the windowing system. While scrolling itself is generally benign and non-destructive, it is an active UI manipulation that can trigger side effects depending on the application context (e.g., auto-loading content, triggering events).

From the tool's definition 滚动屏幕 (scroll screen) — triggers a physical UI interaction (scroll action) on the desktop

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screen_scroll Rate-limited

screen_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": {
    "screen_scroll": {
      "limits": [
        {
          "counter": "screen_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 Screen Agent, so you can run agents against it safely.

FAQ

Questions about screen_scroll

What does the screen_scroll tool do? +

滚动屏幕，用于查看更多内容。. It is categorised as a Execute tool in the Screen Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on screen_scroll? +

Register the Screen Agent MCP server in PolicyLayer and add a rule for screen_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 Screen Agent. Nothing to install.

What risk level is screen_scroll? +

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

Can I rate-limit screen_scroll? +

Yes. Add a rate_limit block to the screen_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 screen_scroll completely? +

Set action: deny in the PolicyLayer policy for screen_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 screen_scroll? +

screen_scroll is provided by the Screen Agent MCP server (lqszhsp/screen-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.