AI agents call computer_cursor_position to retrieve information from LocalAnt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the current position of the mouse cursor—a read-only query with no side effects, no code execution, and no modifications to system state. It falls squarely into the Read category. Severity is low because knowing cursor position poses minimal risk even in an unintended context; it provides only transient information about UI state and cannot be leveraged to cause harm on its own.
From the tool's definition Tool name 'computer_cursor_position' and description 'Get the current mouse cursor position' indicate a query operation that retrieves state information without modifying or executing any actions.
Attacks that exploit this kind of access
Get the current mouse cursor position. It is categorised as a Read tool in the LocalAnt MCP Server, which means it retrieves data without modifying state.
Register the LocalAnt MCP server in PolicyLayer and add a rule for computer_cursor_position: 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 LocalAnt. Nothing to install.
computer_cursor_position is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the computer_cursor_position 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 computer_cursor_position. 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.
computer_cursor_position is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →