Delete events (kind 5)
AI agents call deleteEvent to permanently remove resources in Nostr Tools for AI Agents — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes events from Nostr. While Nostr's distributed nature means copies may persist on some relays, the deletion event (kind 5) signals removal of content the user created, and the action itself cannot be reversed.
From the tool's definition 'Delete events' - irreversible removal of data from the Nostr protocol via kind 5 deletion events. The tool's explicit purpose is to delete, which cannot be undone in a distributed system where events may already be replicated across relays.
Attacks that exploit this kind of access
Delete events (kind 5). It is categorised as a Destructive tool in the Nostr Tools for AI Agents MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nostr Tools for AI Agents MCP server in PolicyLayer and add a rule for deleteEvent: 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 Nostr Tools for AI Agents. Nothing to install.
deleteEvent 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 deleteEvent 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 deleteEvent. 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.
deleteEvent is provided by the Nostr Tools for AI Agents MCP server (jorgenclaw/nostr-mcp-server). 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 →