Delete an entity, its observations, and its relations. Requires confirm=True.
AI agents call forget to permanently remove resources in Memora — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data from the knowledge graph without the ability to undo the deletion. While the blast radius is scoped to a single entity and its relations (not the entire system), the irreversible nature of deletion places it in the Destructive category rather than Write.
From the tool's definition The tool description states: 'Delete an entity, its observations, and its relations.' The verb 'Delete' combined with the requirement to remove an entity and its associated data (observations and relations) from the knowledge graph represents an irreversible…
Attacks that exploit this kind of access
Delete an entity, its observations, and its relations. Requires confirm=True. It is categorised as a Destructive tool in the Memora MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Memora MCP server in PolicyLayer and add a rule for forget: 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 Memora. Nothing to install.
forget 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 forget 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 forget. 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.
forget is provided by the Memora MCP server (vnemaidev/memora). 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 →