scroll_mouse · macOS Control MCP Server MCP: Risk & Policy

WHAT IT DOES

What scroll_mouse does on macOS Control MCP Server

AI agents invoke scroll_mouse to trigger actions in macOS Control MCP Server. 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 scroll_mouse needs a policy

Scrolling the mouse wheel is a GUI interaction/browser action that triggers external operations in whatever application is currently focused. While scrolling alone is relatively low-risk, it is an active desktop automation action (Execute category) that could cause unintended UI effects such as navigating pages, changing values in forms, or triggering scroll-activated behaviors.

From the tool's definition Scroll the mouse wheel — part of a desktop automation server that performs GUI interaction using PyAutoGUI

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scroll_mouse Rate-limited

scroll_mouse 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": {
    "scroll_mouse": {
      "limits": [
        {
          "counter": "scroll_mouse_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 macOS Control MCP Server, so you can run agents against it safely.

FAQ

Questions about scroll_mouse

What does the scroll_mouse tool do? +

Scroll the mouse wheel. It is categorised as a Execute tool in the macOS Control MCP Server 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_mouse? +

Register the macOS Control MCP Server MCP server in PolicyLayer and add a rule for scroll_mouse: 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 MCP Server. Nothing to install.

What risk level is scroll_mouse? +

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

Can I rate-limit scroll_mouse? +

Yes. Add a rate_limit block to the scroll_mouse 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_mouse completely? +

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

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