Press a single named key. Supported keys: return, tab, space, delete, escape,
AI agents invoke keyboard_press 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.
Pressing named keys triggers desktop actions whose effects depend on the current application context. 'Delete' can remove data, 'return' can confirm dialogs or submit forms, and 'escape' can cancel operations. The effects are context-dependent and can cause significant side effects, placing this in the Execute category with medium severity.
From the tool's definition Press a single named key. Supported keys: return, tab, space, delete, escape
Attacks that exploit this kind of access
Press a single named key. Supported keys: return, tab, space, delete, escape,. 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 keyboard_press: 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.
keyboard_press 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 keyboard_press 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 keyboard_press. 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.
keyboard_press is provided by the Computer Use MCP Server MCP server (syedazharmbnr1/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 →