Click a button, link, tab, radio, or checkbox by its visible text. Much more reliable than coordinate clicking. Scrolls element into view before clicking.
AI agents invoke click_by_text to trigger actions in Macos Control. 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 on macOS can trigger any action in any application — submitting forms, deleting files, confirming dialogs, launching processes. The effect is entirely dependent on what element is clicked, making this an Execute-category tool with high blast radius since an AI agent could click destructive or sensitive UI controls.
From the tool's definition 'Click a button, link, tab, radio, or checkbox by its visible text' — triggers UI interactions that can cause arbitrary side effects depending on what element is clicked
Documented attack patterns abuse exactly the kind of access click_by_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Macos Control, and nothing reaches the server without passing your rules. This is the rule we recommend for click_by_text:
{
"version": "1",
"default": "deny",
"tools": {
"click_by_text": {
"limits": [
{
"counter": "click_by_text_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}click_by_text stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Click a button, link, tab, radio, or checkbox by its visible text. Much more reliable than coordinate clicking. Scrolls element into view before clicking. It is categorised as a Execute tool in the Macos Control MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Macos Control MCP server in PolicyLayer and add a rule for click_by_text: 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 Macos Control. Nothing to install.
click_by_text 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 click_by_text 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 click_by_text. 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.
click_by_text is provided by the Macos Control MCP server (peterhdd/macos-control-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Macos Control, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
22 Macos Control tools catalogued and risk-classified — across an index of 43,000+ MCP servers.