Click a UI element by its accessibility label, role, or value — no coordinates needed. More robust than coordinate clicks: survives window moves and layout changes. If element not found, call pilotgentic_ax_tree to discover exact labels, then retry.
AI agents invoke pilotgentic_click_element to trigger actions in PilotGentic. 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.
Clicking UI elements triggers arbitrary application actions depending on what is clicked — submitting forms, confirming dialogs, activating buttons (including destructive or financial ones). The effect is entirely argument-dependent and can be irreversible, making Execute the appropriate category with high severity due to the broad blast radius across any macOS application.
From the tool's definition Click a UI element by its accessibility label, role, or value — no coordinates needed. More robust than coordinate clicks: survives window moves and layout changes.
Attacks that exploit this kind of access
Click a UI element by its accessibility label, role, or value — no coordinates needed. More robust than coordinate clicks: survives window moves and layout changes. If element not found, call pilotgentic_ax_tree to discover exact labels, then retry. It is categorised as a Execute tool in the PilotGentic MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PilotGentic MCP server in PolicyLayer and add a rule for pilotgentic_click_element: 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 PilotGentic. Nothing to install.
pilotgentic_click_element 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 pilotgentic_click_element 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 pilotgentic_click_element. 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.
pilotgentic_click_element is provided by the PilotGentic MCP server (@pilotgentic/mcp-server). 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 →