AI agents invoke scroll_mouse to trigger actions in Macinput. 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.
Scrolling the mouse wheel is a desktop interaction/execution action that can trigger UI events, navigate content, or activate interface elements. It is a browser/desktop action that falls under Execute. While scrolling alone has limited blast radius, it can interact with UI elements in unintended ways (e.g., scrolling through sensitive content, activating scroll-triggered actions).
From the tool's definition 'Scroll the mouse wheel by line units' — triggers a physical mouse scroll action on the desktop GUI
Attacks that exploit this kind of access
Scroll the mouse wheel by line units. It is categorised as a Execute tool in the Macinput MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Macinput 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 Macinput. Nothing to install.
scroll_mouse is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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.
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.
scroll_mouse is provided by the Macinput MCP server (sigma711/macinput). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →