Delete a cell from a local notebook.
AI agents call delete_local_cell to permanently remove resources in Pypi:colab Drive — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of notebook cells cannot be undone by the tool itself and permanently removes code or data. This is an irreversible modification that fits the Destructive category. Severity is high because an AI agent could accidentally or maliciously delete critical cells from research notebooks, losing work. The confidence is high because the intent is unambiguous.
From the tool's definition Tool name contains 'delete' and description states 'Delete a cell from a local notebook' — this irreversibly removes notebook content.
Attacks that exploit this kind of access
Delete a cell from a local notebook. It is categorised as a Destructive tool in the Pypi:colab Drive MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pypi:colab Drive MCP server in PolicyLayer and add a rule for delete_local_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 Pypi:colab Drive. Nothing to install.
delete_local_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 delete_local_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 delete_local_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.
delete_local_cell is provided by the Pypi:colab Drive MCP server (yummytastycode/colab-drive-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 →