shutdown_session
AI agents call shutdown_session to permanently remove resources in Jlab — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name 'shutdown_session' strongly implies terminating a running JupyterLab/SLURM session, which is likely irreversible — any unsaved work, running computations, and allocated HPC resources would be lost. Given the server context (SLURM-managed HPC, GPU-accelerated nodes), shutting down a session could terminate long-running jobs. This maps to Destructive.
From the tool's definition Tool name 'shutdown_session' on a server that manages JupyterLab sessions via SLURM jobs on HPC environments. Description is empty.
Attacks that exploit this kind of access
shutdown_session. It is categorised as a Destructive tool in the Jlab MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Jlab MCP server in PolicyLayer and add a rule for shutdown_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 Jlab. Nothing to install.
shutdown_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 shutdown_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 shutdown_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.
shutdown_session is provided by the Jlab MCP server (kdkyum/jlab-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 →