AI agents invoke press_keys to trigger actions in Computer Control MCP. 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.
On a computer control MCP server with keyboard action capabilities, press_keys almost certainly simulates keyboard input. This is an Execute-category action because it can trigger arbitrary system operations (launching apps, running commands, interacting with UI) depending on what keys are pressed.
From the tool's definition Tool name 'press_keys' on a server providing 'keyboard actions' capabilities; sibling tools include key_down, key_up confirming keyboard control context
Documented attack patterns abuse exactly the kind of access press_keys gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Computer Control MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for press_keys:
{
"version": "1",
"default": "deny",
"tools": {
"press_keys": {
"limits": [
{
"counter": "press_keys_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}press_keys 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_keys. It is categorised as a Execute tool in the Computer Control MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Computer Control MCP server in PolicyLayer and add a rule for press_keys: 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 Computer Control MCP. Nothing to install.
press_keys 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_keys 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_keys. 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_keys is provided by the Computer Control MCP server (ab498/computer-control-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 15 Computer Control MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
15 Computer Control MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.