Delete a short URL
AI agents call delete_url to permanently remove resources in YOURLS-MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of URL mappings cannot be undone and represents loss of service for any users or systems relying on that short URL redirect. While the blast radius is limited to the URL shortening service (not system-wide or financial), the irreversible nature and removal of functionality classifies this as Destructive rather than Write.
From the tool's definition Tool name explicitly states 'delete_url' and description confirms 'Delete a short URL' — this irreversibly removes data from the YOURLS database.
Attacks that exploit this kind of access
Delete a short URL. It is categorised as a Destructive tool in the YOURLS-MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the YOURLS- MCP server in PolicyLayer and add a rule for delete_url: 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 YOURLS-MCP. Nothing to install.
delete_url 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_url 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_url. 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_url is provided by the YOURLS- MCP server (kesslerio/yourls-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
delete_url is one line of YOURLS-'s registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →