Scroll at specific coordinates or current mouse position. Use wheel_times to control scroll amount (1 wheel = ~3-5 lines). Essential for navigating lists, web pages, and long content.
AI agents invoke Scroll-Tool to trigger actions in Windows-MCP. 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 is an active UI interaction that sends input events to the operating system, similar to clicking or dragging. While it doesn't directly modify data, it is an Execute-class action because it triggers external operations (UI input events) whose effects depend on arguments (coordinates, scroll amount).
From the tool's definition 'Scroll at specific coordinates or current mouse position' — triggers a UI automation action (mouse wheel event) on the Windows system, and exists within a server that 'interact[s] with Windows operating systems' via 'UI automation'
Attacks that exploit this kind of access
Scroll at specific coordinates or current mouse position. Use wheel_times to control scroll amount (1 wheel = ~3-5 lines). Essential for navigating lists, web pages, and long content. It is categorised as a Execute tool in the Windows-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Windows- MCP server in PolicyLayer and add a rule for Scroll-Tool: 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 Windows-MCP. Nothing to install.
Scroll-Tool 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-Tool 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-Tool. 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-Tool is provided by the Windows- MCP server (zhouke2020/cursortouch-windows-mcp). 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 →