Reset memo state. Default drops only the manual override row
AI agents call memo_reset to permanently remove resources in Llama — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool drops a database row (the manual override) which is an irreversible destructive action. While the scope is limited to a single row by default, 'reset' and 'drops' clearly indicate data deletion that cannot be undone, warranting a Destructive classification with high severity given it affects memo state on a business platform.
From the tool's definition 'Reset memo state' and 'drops only the manual override row' — 'drops' indicates irreversible deletion of data
Attacks that exploit this kind of access
Reset memo state. Default drops only the manual override row. It is categorised as a Destructive tool in the Llama MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Llama MCP server in PolicyLayer and add a rule for memo_reset: 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 Llama. Nothing to install.
memo_reset 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 memo_reset 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 memo_reset. 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.
memo_reset is provided by the Llama MCP server (llama-ventures/llama-cli). 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 →