Scroll the mouse wheel on the target PC.
AI agents invoke mouse_scroll to trigger actions in Mcp Serial Hid Kvm. 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.
mouse_scroll executes a physical input operation (mouse wheel scroll) on a remote physical PC through a KVM interface. This is an Execute-category action because it triggers an external operation whose effects depend on arguments (scroll direction, amount, position).
From the tool's definition 'Scroll the mouse wheel on the target PC' — triggers a physical input action on a remote machine via KVM
Attacks that exploit this kind of access
Scroll the mouse wheel on the target PC. It is categorised as a Execute tool in the Mcp Serial Hid Kvm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Serial Hid Kvm MCP server in PolicyLayer and add a rule for mouse_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 Mcp Serial Hid Kvm. Nothing to install.
mouse_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 mouse_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 mouse_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.
mouse_scroll is provided by the Mcp Serial Hid Kvm MCP server (sunasaji/mcp-serial-hid-kvm). 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 →