AI agents call cmux_close_window to permanently remove resources in Cmux Agent — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Closing a window in a terminal multiplexer like tmux/cmux permanently destroys the window and all associated panes and running processes. This cannot be undone — any unsaved work or running sessions are lost. This qualifies as Destructive due to the irreversible nature of the action. Severity is high because it can terminate multiple parallel AI CLI sessions and browser instances at once.
From the tool's definition 'Close a window' — closing a window is an irreversible action that terminates the window and any sessions/panes running within it, destroying their state.
Documented attack patterns abuse exactly the kind of access cmux_close_window gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cmux Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for cmux_close_window:
{
"version": "1",
"default": "deny",
"hide": [
"cmux_close_window"
]
} cmux_close_window disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Close a window. It is categorised as a Destructive tool in the Cmux Agent MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cmux Agent MCP server in PolicyLayer and add a rule for cmux_close_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 Cmux Agent. Nothing to install.
cmux_close_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 cmux_close_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 cmux_close_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.
cmux_close_window is provided by the Cmux Agent MCP server (multiagentcognition/cmux-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cmux Agent, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
63 Cmux Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.