scroll

THE RISK

High Risk

Why scroll needs a policy

Scrolling is an external UI operation that affects application state (viewport position, potentially triggering lazy-load events or UI changes). It's not purely reading data, and it interacts with the live OS environment. It belongs to Execute as it performs a browser/UI action whose effects depend on arguments (scroll position, direction, application context).

From the tool's definition 'Scroll in the frontmost application' — triggers a UI interaction/action in a live macOS application

Documented attack patterns abuse exactly the kind of access scroll gives an agent:

POLICY

How to control scroll

PolicyLayer is an MCP gateway — it sits between your AI agents and Macos Control, and nothing reaches the server without passing your rules. This is the rule we recommend for scroll:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "scroll": {
      "limits": [
        {
          "counter": "scroll_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

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.

Create a free account and register Macos Control — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Macos Control tools

Execute execute_javascript Run JavaScript in the active browser tab. Much faster than screenshot+OCR for web pages. R Execute launch_app Open or focus a macOS application by name. Prefer batch_actions when combining with other Execute batch_actions PREFERRED: Always use this tool instead of calling individual action tools (click_at, type Execute click_at Click at x,y screen coordinates. Returns a screenshot by default (disable with return_scre Execute click_by_text Click a button, link, tab, radio, or checkbox by its visible text. Much more reliable than Execute click_element Click a named UI element in an app window. Returns a screenshot by default (disable with r Execute double_click_at Double-click at x,y screen coordinates. Returns a screenshot by default (disable with retu Execute open_url Open a URL in Safari or Chrome.

All 22 Macos Control tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Macos Control → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about scroll

What does the scroll tool do? +

Scroll in the frontmost application. Prefer batch_actions when combining with other actions. It is categorised as a Execute tool in the Macos Control MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on scroll? +

Register the Macos Control MCP server in PolicyLayer and add a rule for 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 Macos Control. Nothing to install.

What risk level is scroll? +

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

Can I rate-limit scroll? +

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

Set action: deny in the PolicyLayer policy for 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 scroll? +

scroll is provided by the Macos Control MCP server (peterhdd/macos-control-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Macos Control tool call.

Start from Macos Control, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →