Delete a document (soft-delete). Only the document owner can delete. Returns 204 on success.
AI agents call delete_lightpaper to permanently remove resources in Lightpaper Mcp — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the deletion is described as a 'soft-delete' (which may preserve data at the database level for recovery), from the user's perspective this tool irreversibly removes access to published content. This is a destructive operation that cannot be undone through normal tool usage.
From the tool's definition Tool name is 'delete_lightpaper' and description states 'Delete a document (soft-delete)'. The word 'Delete' combined with the action of removing a document from the platform indicates data destruction.
Attacks that exploit this kind of access
Delete a document (soft-delete). Only the document owner can delete. Returns 204 on success. It is categorised as a Destructive tool in the Lightpaper Mcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lightpaper MCP server in PolicyLayer and add a rule for delete_lightpaper: 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 Lightpaper Mcp. Nothing to install.
delete_lightpaper 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_lightpaper 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_lightpaper. 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_lightpaper is provided by the Lightpaper MCP server (pypi:lightpaper-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 →