Kill (close) a pane.
AI agents call kill_pane to permanently remove resources in TmuxControlLib MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Killing a tmux pane terminates the pane and any process running inside it. This action is irreversible — the pane, its scrollback history, and any unsaved state are permanently lost. This matches the Destructive category. Severity is high because misuse could terminate critical running processes (e.g., servers, long-running jobs) with no recovery path.
From the tool's definition Kill (close) a pane — 'kill' indicates irreversible termination of the pane and any running process within it.
Attacks that exploit this kind of access
Kill (close) a pane. It is categorised as a Destructive tool in the TmuxControlLib MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TmuxControlLib MCP Server MCP server in PolicyLayer and add a rule for kill_pane: 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 TmuxControlLib MCP Server. Nothing to install.
kill_pane is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the kill_pane 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 kill_pane. 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.
kill_pane is provided by the TmuxControlLib MCP Server MCP server (jbwinters/tmuxcontrollib). 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 →