Hold down a key (must call key_up to release).
AI agents invoke key_down to trigger actions in macOS Control MCP Server. 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.
This tool simulates keyboard input by holding down a key on the system. It can trigger arbitrary keyboard shortcuts, modify system settings, or interact with any application. Combined with other tools in this server (hotkey, click_mouse, etc.), it enables full desktop automation that could be misused to execute commands, manipulate files, or control the OS.
From the tool's definition Hold down a key (must call key_up to release)
Attacks that exploit this kind of access
Hold down a key (must call key_up to release). It is categorised as a Execute tool in the macOS Control MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the macOS Control MCP Server MCP server in PolicyLayer and add a rule for key_down: 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 MCP Server. Nothing to install.
key_down 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 key_down 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 key_down. 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.
key_down is provided by the macOS Control MCP Server MCP server (lodimup/macos-control-mcp). 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 →