ipynb_delete_cell
AI agents call ipynb_delete_cell to permanently remove resources in Jupyter Editor — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting cells from a notebook cannot be undone without a prior backup or version control. This is a destructive operation with permanent data loss potential. An AI agent could maliciously remove critical code, analysis, or documentation. Severity is high (not critical) because impact is scoped to a single notebook file, not system-wide or multi-file destruction.
From the tool's definition Tool name 'ipynb_delete_cell' indicates irreversible deletion of notebook cells. Sibling tools include 'ipynb_delete_cells_batch' and 'ipynb_clear_outputs', confirming this server offers destructive operations.
Attacks that exploit this kind of access
ipynb_delete_cell. It is categorised as a Destructive tool in the Jupyter Editor MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Jupyter Editor MCP server in PolicyLayer and add a rule for ipynb_delete_cell: 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 Jupyter Editor. Nothing to install.
ipynb_delete_cell 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 ipynb_delete_cell 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 ipynb_delete_cell. 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.
ipynb_delete_cell is provided by the Jupyter Editor MCP server (jsamuel1/jupyter-editor-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 →