Delete all your shortened URLs.
AI agents call delete_all_urls to permanently remove resources in Url Shortener — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion of all shortened URLs owned by the user. Destructive is the appropriate category as the action cannot be undone and results in complete data loss. Severity is high because while the blast radius is limited to the user's own URL collection, the totality of deletion (all URLs) and irreversibility warrant high severity.
From the tool's definition Tool name is 'delete_all_urls' and description states 'Delete all your shortened URLs.' The verb 'delete' combined with 'all' indicates irreversible removal of data at scale.
Attacks that exploit this kind of access
Delete all your shortened URLs. It is categorised as a Destructive tool in the Url Shortener MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Url Shortener MCP server in PolicyLayer and add a rule for delete_all_urls: 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 Url Shortener. Nothing to install.
delete_all_urls 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_all_urls 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_all_urls. 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_all_urls is provided by the Url Shortener MCP server (michaelshumshum/url-shortener-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 →