Delete a notebook file and shut down its kernel if running.
AI agents call notebook_delete to permanently remove resources in JupyterMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Notebook deletion is a destructive operation that irreversibly removes files and cannot be undone through normal means. While the severity is not critical (it affects only one notebook file, not systems or multiple resources), it clearly falls into the Destructive category as it permanently erases user data.
From the tool's definition Tool deletes a notebook file (irreversible data loss) and shuts down its kernel. Description explicitly states 'Delete a notebook file' which removes data that cannot be recovered unless backed up.
Attacks that exploit this kind of access
Delete a notebook file and shut down its kernel if running. It is categorised as a Destructive tool in the JupyterMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Jupyter MCP server in PolicyLayer and add a rule for notebook_delete: 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 JupyterMCP. Nothing to install.
notebook_delete 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 notebook_delete 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 notebook_delete. 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.
notebook_delete is provided by the Jupyter MCP server (try3d/jupytermcp). 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 →