Kill/terminate a tmux session and all its windows and panes.
AI agents call tmux_kill_session to permanently remove resources in Tmux MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly destroys a tmux session along with all its windows and panes. Any running processes, unsaved terminal state, or work-in-progress commands within those panes are permanently lost. This is a classic destructive operation with no undo mechanism.
From the tool's definition Kill/terminate a tmux session and all its windows and panes
Attacks that exploit this kind of access
Kill/terminate a tmux session and all its windows and panes. It is categorised as a Destructive tool in the Tmux MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tmux MCP Server MCP server in PolicyLayer and add a rule for tmux_kill_session: 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 Tmux MCP Server. Nothing to install.
tmux_kill_session 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 tmux_kill_session 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 tmux_kill_session. 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.
tmux_kill_session is provided by the Tmux MCP Server MCP server (mediocretriumph/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 →