hippo_forget
FORGIA #195. Delete one episode by id (privacy / GDPR).
This record as markdown: /tools/verimem/hippo-forget.md
What hippo_forget does on Verimem
AI agents call hippo_forget to permanently remove resources in Verimem, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why hippo_forget is rated Critical
This tool deletes data by episode ID and cannot be undone. Although the deletion serves a legitimate privacy/GDPR purpose, the action is inherently destructive. The blast radius is high if misused by an AI agent that could delete critical memory episodes needed for correct operation or audit trails. Classified as Destructive rather than Write because deletion is irreversible.
From the tool's definition Delete one episode by id (privacy / GDPR) — the tool explicitly performs irreversible deletion of stored memory episodes.
Attacks that exploit this kind of access
The rule that runs hippo_forget safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Verimem, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For hippo_forget, this is the rule to start with:
hippo_forget is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Verimem, apply this rule, and every hippo_forget call is checked against it from then on.
Questions about hippo_forget
FORGIA #195. Delete one episode by id (privacy / GDPR). It is categorised as a Destructive tool in the Verimem MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Verimem MCP server in PolicyLayer and add a rule for hippo_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 Verimem. Nothing to install.
hippo_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 hippo_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 hippo_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.
hippo_forget is provided by the Verimem MCP server (aureliocpr-ctrl/verimem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Verimem, and thousands of servers like it.
Across the catalogue