Terminate a terminal session
AI agents call kill_terminal to permanently remove resources in Persistent Terminal MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Killing a terminal session is irreversible — any unsaved work, running processes, or state within that session is permanently lost. This constitutes destructive action that cannot be undone, warranting high severity due to potential loss of running jobs, data, or session state.
From the tool's definition Tool name 'kill_terminal' and description 'Terminate a terminal session' clearly indicate irreversible destruction of a running process/session.
Attacks that exploit this kind of access
Terminate a terminal session. It is categorised as a Destructive tool in the Persistent Terminal MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Persistent Terminal MCP Server MCP server in PolicyLayer and add a rule for kill_terminal: 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 Persistent Terminal MCP Server. Nothing to install.
kill_terminal 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_terminal 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_terminal. 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_terminal is provided by the Persistent Terminal MCP Server MCP server (masx200/persistent-terminal-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 →