Send a single key press with optional modifier keys (e.g., Ctrl+C, Alt+F4).
AI agents invoke send_key to trigger actions in Mcp Serial Hid Kvm. 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 executes keyboard input on a remote physical machine. While a single key press seems innocuous, the ability to send arbitrary key combinations (e.g., Alt+F4, Ctrl+Alt+Del, or destructive shortcuts) to a physical PC constitutes execution of external operations.
From the tool's definition 'Send a single key press with optional modifier keys (e.g., Ctrl+C, Alt+F4)' — triggers external keyboard input operations on a physical PC
Attacks that exploit this kind of access
Send a single key press with optional modifier keys (e.g., Ctrl+C, Alt+F4). It is categorised as a Execute tool in the Mcp Serial Hid Kvm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Serial Hid Kvm MCP server in PolicyLayer and add a rule for send_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 Mcp Serial Hid Kvm. Nothing to install.
send_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 send_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 send_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.
send_key is provided by the Mcp Serial Hid Kvm MCP server (sunasaji/mcp-serial-hid-kvm). 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 →