screen_learn_scroll · Screen Agent MCP: Risk & Policy

WHAT IT DOES

What screen_learn_scroll does on Screen Agent

AI agents invoke screen_learn_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_learn_scroll needs a policy

This tool performs scrolling actions on the desktop (an external UI operation), then auto-scrolls back. It triggers real UI interactions rather than merely reading data passively, placing it in the Execute category. Severity is medium because it interacts with live desktop state, though the auto-revert reduces blast radius.

From the tool's definition '通过滚动学习屏幕内容' (learn screen content via scrolling) and '会自动回滚到原位置' (automatically scrolls back to original position) — triggers physical scroll actions on the desktop UI

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screen_learn_scroll Rate-limited

screen_learn_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_learn_scroll": {
      "limits": [
        {
          "counter": "screen_learn_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_learn_scroll

What does the screen_learn_scroll tool do? +

通过滚动学习屏幕内容，会自动回滚到原位置。. 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_learn_scroll? +

Register the Screen Agent MCP server in PolicyLayer and add a rule for screen_learn_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_learn_scroll? +

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

Can I rate-limit screen_learn_scroll? +

Yes. Add a rate_limit block to the screen_learn_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_learn_scroll completely? +

Set action: deny in the PolicyLayer policy for screen_learn_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_learn_scroll? +

screen_learn_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.