Forget memories by explicit selector. Requires a reason and defaults to soft delete.
AI agents call memory_forget to permanently remove resources in Lore Context — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
While the tool permits soft-deletion (which may be technically reversible depending on implementation), the primary function is to remove data by explicit selector, matching the Destructive category definition. The requirement for a reason suggests this is a controlled but powerful operation.
From the tool's definition 'Forget memories by explicit selector' with 'soft delete' as default—this irreversibly removes stored agent memories from the context system.
Attacks that exploit this kind of access
Forget memories by explicit selector. Requires a reason and defaults to soft delete. It is categorised as a Destructive tool in the Lore Context MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lore Context MCP server in PolicyLayer and add a rule for memory_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 Lore Context. Nothing to install.
memory_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 memory_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 memory_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.
memory_forget is provided by the Lore Context MCP server (Lore-Context/lore-context). 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 →