AI agents invoke press_key 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.
Pressing key combinations on a live macOS system constitutes executing external operations. Key combos can trigger arbitrary system-level actions (e.g., Cmd+Q to quit apps, Cmd+Space to open Spotlight, Cmd+Delete to delete files), making misuse potentially destructive or system-disruptive. Classified as Execute since the actual effect depends on context/arguments, with high severity due to broad blast radius.
From the tool's definition press_key — 'Press a key combo (e.g. press...' — triggers keyboard input actions on the macOS system
Documented attack patterns abuse exactly the kind of access press_key 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 press_key:
{
"version": "1",
"default": "deny",
"tools": {
"press_key": {
"limits": [
{
"counter": "press_key_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}press_key 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.
Press a key combo (e.g. press. 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 press_key: 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.
press_key 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 press_key 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 press_key. 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.
press_key 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.