Delete a cell from a notebook by its cell ID.
AI agents call cell_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.
Deletion of notebook cells is an irreversible operation that destroys data without the ability to undo through the tool itself. While notebooks may have version control or undo features externally, the tool's direct action is destructive. This is more severe than Write (which is reversible modification) and constitutes a destructive category action.
From the tool's definition Tool name is 'cell_delete' and description states 'Delete a cell from a notebook by its cell ID.' The verb 'delete' and action of removing a cell are irreversible operations.
Attacks that exploit this kind of access
Delete a cell from a notebook by its cell ID. 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 cell_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.
cell_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 cell_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 cell_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.
cell_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 →