AI agents invoke press_keyboard_key to trigger actions in Macinput. 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 keyboard keys with modifiers (e.g., Cmd+Q, Cmd+Delete, Ctrl+Alt+Del) can trigger arbitrary system actions, launch/close applications, delete files, or execute commands. This is an Execute-category tool because it drives external system operations whose effects depend on which keys are pressed.
From the tool's definition 'Press and release a key with optional modifiers' on a macOS desktop GUI automation server that 'enables AI agents to control the desktop GUI through keyboard input'
Attacks that exploit this kind of access
Press and release a key with optional modifiers. It is categorised as a Execute tool in the Macinput MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Macinput MCP server in PolicyLayer and add a rule for press_keyboard_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 Macinput. Nothing to install.
press_keyboard_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_keyboard_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_keyboard_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_keyboard_key is provided by the Macinput MCP server (sigma711/macinput). 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 →