Tap a key (e.g.,
AI agents invoke vnc_key_tap to trigger actions in VNC 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.
Sending keystrokes to a remote computer is an Execute-level action: it triggers external operations (keypresses) whose effects entirely depend on the current state of the remote system and what keys are sent. Misuse could trigger arbitrary actions (e.g., Enter to confirm dialogs, shortcuts to delete files, or keyboard shortcuts for financial transactions).
From the tool's definition 'Tap a key' — triggers keyboard input on a remote computer via VNC, performing direct input control on the target system
Attacks that exploit this kind of access
Tap a key (e.g.,. It is categorised as a Execute tool in the VNC MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the VNC MCP Server MCP server in PolicyLayer and add a rule for vnc_key_tap: 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 VNC MCP Server. Nothing to install.
vnc_key_tap 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 vnc_key_tap 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 vnc_key_tap. 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.
vnc_key_tap is provided by the VNC MCP Server MCP server (volkan-m/vnc-mcp-server). 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 →