Kill a window and all its panes.
AI agents call kill_window to permanently remove resources in Post-Exploitation tmux MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Killing a tmux window permanently destroys it along with all panes and their running processes. This cannot be undone, making it Destructive. The blast radius is high because it can terminate multiple running processes/sessions simultaneously, potentially disrupting active work or services managed by an AI agent.
From the tool's definition 'Kill a window and all its panes' — terminating a window and all its panes is an irreversible destruction of those tmux entities and any processes running within them.
Attacks that exploit this kind of access
Kill a window and all its panes. It is categorised as a Destructive tool in the Post-Exploitation tmux MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Post-Exploitation tmux MCP Server MCP server in PolicyLayer and add a rule for kill_window: 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 Post-Exploitation tmux MCP Server. Nothing to install.
kill_window 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_window 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_window. 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_window is provided by the Post-Exploitation tmux MCP Server MCP server (raghavansv/tmux-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 →