Critical Risk →

memory_forget

Remove a memory by searching for the closest match and deactivating it.

How to control memory_forget ↓

AI agents call memory_forget to permanently remove resources in ClawMem — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

This tool permanently removes or deactivates memories from the on-device persistence layer. Although the description uses 'deactivating' rather than 'deleting', the functional effect is to remove data from the agent's ability to recall it, making the memory unavailable for future sessions. This is an irreversible operation that cannot be undone—matching the Destructive category.

From the tool's definition Tool name 'memory_forget' and description 'Remove a memory' and 'deactivating it' indicate irreversible deletion or deactivation of stored data.

Documented attack patterns abuse exactly the kind of access memory_forget gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and ClawMem, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_forget:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "memory_forget"
  ]
}

memory_forget disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register ClawMem — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Go deeper

What does the memory_forget tool do? +

Remove a memory by searching for the closest match and deactivating it. It is categorised as a Destructive tool in the ClawMem MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on memory_forget? +

Register the ClawMem 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 ClawMem. Nothing to install.

What risk level is memory_forget? +

memory_forget is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit memory_forget? +

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.

How do I block memory_forget completely? +

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.

What MCP server provides memory_forget? +

memory_forget is provided by the ClawMem MCP server (yoloshii/clawmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every ClawMem tool call.

Deterministic rules across all 30 ClawMem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

30 ClawMem tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.