Remove old/unused patterns (zero match_count, older than max_age_days).
AI agents call patterns_prune to permanently remove resources in Ensemble — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly deletes data (patterns) from the vector memory system based on automatic criteria (age and match count). This is a destructive operation that cannot be undone. While the blast radius depends on whether patterns are redundant or critical to agent function, the deletion itself is irreversible.
From the tool's definition Remove old/unused patterns (zero match_count, older than max_age_days) — explicitly describes deletion of patterns based on age and usage criteria.
Attacks that exploit this kind of access
Remove old/unused patterns (zero match_count, older than max_age_days). It is categorised as a Destructive tool in the Ensemble MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ensemble MCP server in PolicyLayer and add a rule for patterns_prune: 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 Ensemble. Nothing to install.
patterns_prune 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 patterns_prune 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 patterns_prune. 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.
patterns_prune is provided by the Ensemble MCP server (lynkbyte/ensemble). 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 →