AI agents invoke computer_left_click to trigger actions in LocalAnt. 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 is an active browser/desktop automation action that triggers external operations depending on where the click lands. The effect is entirely argument-dependent — a click can submit forms, launch applications, delete files via GUI, etc. — making it Execute.
From the tool's definition Left-click at x,y (screenshot coordinates). Requires approval (risk 3).
Attacks that exploit this kind of access
Left-click at x,y (screenshot coordinates). Requires approval (risk 3). It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LocalAnt MCP server in PolicyLayer and add a rule for computer_left_click: 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_left_click 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 computer_left_click 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_left_click. 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_left_click 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.
computer_left_click is one line of LocalAnt's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →