Manually delete a memory by ID.
AI agents call vrm_forget to permanently remove resources in Verified Repo Memory — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes repository-scoped memory records by ID. Deletion is irreversible and cannot be undone. While the blast radius is scoped to a single memory item (not system-wide data destruction), deletion of critical memories could degrade repository context, cause loss of important citations or decision history, and disrupt downstream processes relying on that memory.
From the tool's definition Tool name is 'vrm_forget' and description states 'Manually delete a memory by ID' — explicitly performs deletion, which is irreversible.
Attacks that exploit this kind of access
Manually delete a memory by ID. It is categorised as a Destructive tool in the Verified Repo Memory MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Verified Repo Memory MCP server in PolicyLayer and add a rule for vrm_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 Verified Repo Memory. Nothing to install.
vrm_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 vrm_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 vrm_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.
vrm_forget is provided by the Verified Repo Memory MCP server (cognitivemyriad/mcp-verified-repo-memory). 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 →