Run retention policy to archive old, low-value observations.
AI agents call mem_cleanup to permanently remove resources in Qontinui MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Archiving under a retention policy typically involves irreversibly removing or moving data (old, low-value observations) from active storage. The phrase 'archive' can be considered a one-way, potentially irreversible operation (data is removed from primary storage and may not be easily recoverable). This qualifies as Destructive rather than Write.
From the tool's definition Run retention policy to archive old, low-value observations
Attacks that exploit this kind of access
Run retention policy to archive old, low-value observations. It is categorised as a Destructive tool in the Qontinui MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Qontinui MCP Server MCP server in PolicyLayer and add a rule for mem_cleanup: 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 Qontinui MCP Server. Nothing to install.
mem_cleanup 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 mem_cleanup 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 mem_cleanup. 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.
mem_cleanup is provided by the Qontinui MCP Server MCP server (qontinui/qontinui-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 →