Delete multiple patterns from the database
AI agents call delete_patterns to permanently remove resources in MCPatterns — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes patterns from persistent storage with no undo mechanism. Deletion of multiple records at once increases blast radius. An AI agent with access could maliciously or erroneously purge a user's entire pattern library, destroying their custom coding conventions and development memory.
From the tool's definition Tool name is 'delete_patterns' and description states 'Delete multiple patterns from the database' — explicit irreversible deletion of stored data.
Attacks that exploit this kind of access
Delete multiple patterns from the database. It is categorised as a Destructive tool in the MCPatterns MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCPatterns MCP server in PolicyLayer and add a rule for delete_patterns: 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 MCPatterns. Nothing to install.
delete_patterns 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_patterns 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_patterns. 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_patterns is provided by the MCPatterns MCP server (nicholasrubright/mcpatterns). 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 →