Scroll at the specified screen coordinates. Positive amount scrolls down, negative scrolls up. Optionally scroll horizontally. Moves the mouse to the target position first, then performs the scroll. NOTE: The target app must be frontmost for scroll events to reach it — use focus_window or click f...
AI agents invoke scroll to trigger actions in MacWright. 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.
This tool performs a native macOS UI interaction (mouse movement + scroll event injection via CGEvents) that triggers external operations on the desktop environment. It's not purely reading data, and its effects depend on the arguments (coordinates, amount). It falls under Execute as it triggers system-level input events that affect the state of the running desktop and applications.
From the tool's definition Scroll at the specified screen coordinates...Moves the mouse to the target position first, then performs the scroll...CGEvents scroll whatever element is under the cursor
Attacks that exploit this kind of access
Scroll at the specified screen coordinates. Positive amount scrolls down, negative scrolls up. Optionally scroll horizontally. Moves the mouse to the target position first, then performs the scroll. NOTE: The target app must be frontmost for scroll events to reach it — use focus_window or click first if needed. CGEvents scroll whatever element is under the cursor — use this to scroll custom overflow containers in web pages by aiming coordinates inside the scrollable div. For page-level (window) scrolling in Safari, prefer scroll_page. horizontalAmount may not move web scrollX since browsers intercept horizontal wheel events differently. It is categorised as a Execute tool in the MacWright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MacWright 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 MacWright. Nothing to install.
scroll 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 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. 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 is provided by the MacWright MCP server (ruchit-p/macwright). 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 →