Delete a node (and all its children) from the document.
AI agents call delete_node to permanently remove resources in Pen — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of document nodes cannot be undone and affects both the target node and all descendants. This is an irreversible operation that destroys data structure. While not financial, it is more severe than Write (reversible modification) and qualifies as Destructive. High severity reflects the potential to corrupt document structure and lose content if misused by an agent.
From the tool's definition Tool name 'delete_node' explicitly performs deletion. Description states 'Delete a node (and all its children) from the document' — a cascading, irreversible action that removes data and any dependent child nodes.
Attacks that exploit this kind of access
Delete a node (and all its children) from the document. It is categorised as a Destructive tool in the Pen MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pen MCP server in PolicyLayer and add a rule for delete_node: 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 Pen. Nothing to install.
delete_node 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_node 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_node. 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_node is provided by the Pen MCP server (@zseven-w/pen-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 →