Terminate a Claude-Code session.
AI agents call terminate_session to permanently remove resources in Claude Code MCP Controller — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Terminating a session is a destructive, irreversible action. Once a Claude Code session is terminated, any unsaved state, context, or in-progress work is lost and cannot be recovered. This has a high blast radius because an AI agent misusing this tool could abruptly end active work sessions, potentially losing significant progress or interrupting critical ongoing tasks.
From the tool's definition 'Terminate a Claude-Code session' — terminating a session is an irreversible action that ends the session and destroys its state
Attacks that exploit this kind of access
Terminate a Claude-Code session. It is categorised as a Destructive tool in the Claude Code MCP Controller MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Code MCP Controller MCP server in PolicyLayer and add a rule for terminate_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 Claude Code MCP Controller. Nothing to install.
terminate_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 terminate_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 terminate_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.
terminate_session is provided by the Claude Code MCP Controller MCP server (mostafa-drz/claude-code-mcp-controller). 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 →