Press a key or key combination. Use xdotool key names:
AI agents invoke computer_key to trigger actions in Computer Use 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 at the OS level via xdotool, triggering arbitrary key presses and combinations on a live desktop. An AI agent could misuse this to execute system commands (e.g., opening terminals, triggering shortcuts like Alt+F4, Ctrl+Alt+T), delete files, or interact with any focused application in unintended ways.
From the tool's definition Press a key or key combination. Use xdotool key names
Attacks that exploit this kind of access
Press a key or key combination. Use xdotool key names:. It is categorised as a Execute tool in the Computer Use MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Computer Use MCP Server MCP server in PolicyLayer and add a rule for computer_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 Computer Use MCP Server. Nothing to install.
computer_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 computer_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 computer_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.
computer_key is provided by the Computer Use MCP Server MCP server (sebastianbaltes/claude_code_computer_use_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 →