Scroll at ref/coords by pixel delta.
AI agents invoke scroll to trigger actions in Linux Computer Use. 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 a browser/desktop action that manipulates the UI state. It falls under Execute because it triggers an external operation on the controlled desktop. While scrolling alone has limited blast radius, it can be used to navigate interfaces and expose or interact with content, making it medium severity in context of a desktop control agent.
From the tool's definition 'Scroll at ref/coords by pixel delta' — triggers a physical UI interaction (scroll action) on the desktop via xdotool/AT-SPI, which is an external operation whose effect depends on arguments (position and delta).
Attacks that exploit this kind of access
Scroll at ref/coords by pixel delta. It is categorised as a Execute tool in the Linux Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Linux Computer Use 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 Linux Computer Use. 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 Linux Computer Use MCP server (tak-uukti/linux-computer-use). 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 →