Kill the tmux session and remove its stored metadata.
AI agents call session_destroy to permanently remove resources in Claude Code — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible destruction of session state and metadata. Although no user data external to the session is deleted, the session itself and its history/context are permanently removed. This is a destructive action (rather than merely Execute) because it cannot be undone—once killed and metadata removed, the session is gone.
From the tool's definition "Kill the tmux session and remove its stored metadata" — the tool irreversibly terminates an active session and deletes its associated metadata, which cannot be recovered.
Attacks that exploit this kind of access
Kill the tmux session and remove its stored metadata. It is categorised as a Destructive tool in the Claude Code MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Code MCP server in PolicyLayer and add a rule for session_destroy: 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 Claude Code. Nothing to install.
session_destroy 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 session_destroy 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 session_destroy. 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.
session_destroy is provided by the Claude Code MCP server (joschi655/claude-code-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 →