Deletes a prompt by its ID
AI agents call delete_prompt to permanently remove resources in Promptopia MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a prompt resource. Deletion is irreversible and cannot be undone through normal operations. While the blast radius is confined to prompt artifacts (not data exfiltration or financial harm), the destructive nature and potential for data loss if misapplied by an AI agent justifies a 'high' severity rating and Destructive category classification.
From the tool's definition Tool name is 'delete_prompt' and description states 'Deletes a prompt by its ID' — the verb 'deletes' indicates irreversible removal of data.
Attacks that exploit this kind of access
Deletes a prompt by its ID. It is categorised as a Destructive tool in the Promptopia MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Promptopia MCP server in PolicyLayer and add a rule for delete_prompt: 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 Promptopia MCP. Nothing to install.
delete_prompt 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_prompt 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_prompt. 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_prompt is provided by the Promptopia MCP server (lumile/promptopia-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 →