Send a keyboard shortcut (multiple keys pressed simultaneously). Example: Ctrl+Alt+Delete
AI agents invoke pikvm_shortcut to trigger actions in PiKVM 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 sends keyboard shortcuts to a physical machine via PiKVM, triggering real OS-level actions. Shortcuts like Ctrl+Alt+Delete can reboot systems, Ctrl+W can close applications, Alt+F4 can terminate programs, etc. These are external operations with real-world effects on a physical machine.
From the tool's definition Send a keyboard shortcut (multiple keys pressed simultaneously). Example: Ctrl+Alt+Delete
Attacks that exploit this kind of access
Send a keyboard shortcut (multiple keys pressed simultaneously). Example: Ctrl+Alt+Delete. It is categorised as a Execute tool in the PiKVM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PiKVM MCP Server MCP server in PolicyLayer and add a rule for pikvm_shortcut: 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 PiKVM MCP Server. Nothing to install.
pikvm_shortcut 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 pikvm_shortcut 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 pikvm_shortcut. 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.
pikvm_shortcut is provided by the PiKVM MCP Server MCP server (kultivatorconsulting/pikvm_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 →