Critical Risk →

forget_memories

Delete memory entries matching filters. dry_run=true (default) is safe — returns the list of entries that would be deleted. Pinned entries are never forgotten. At least one filter required. Owner only — registered handle + secret required.

Risk signalsHandles credentials or secrets (secret)

Part of the Gateway server.

forget_memories can permanently delete data in Gateway, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE GATEWAY →

Free to start. No card required.

AI agents may call forget_memories to permanently remove or destroy resources in Gateway. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.

Without a policy, an AI agent could call forget_memories in a loop, permanently destroying resources in Gateway. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

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

See the full Gateway policy for all 42 tools.

Get this rule live on your own Gateway server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY GATEWAY →

View all 42 tools →

These attack patterns abuse exactly the kind of access forget_memories gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so forget_memories only ever does what you allow.

SECURE GATEWAY →

Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.

What does the forget_memories tool do? +

Delete memory entries matching filters. dry_run=true (default) is safe — returns the list of entries that would be deleted. Pinned entries are never forgotten. At least one filter required. Owner only — registered handle + secret required.. It is categorised as a Destructive tool in the Gateway 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 forget_memories? +

Register the Gateway MCP server in PolicyLayer and add a rule for forget_memories: 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 Gateway. Nothing to install.

What risk level is forget_memories? +

forget_memories 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 forget_memories? +

Yes. Add a rate_limit block to the forget_memories 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 forget_memories completely? +

Set action: deny in the PolicyLayer policy for forget_memories. 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 forget_memories? +

forget_memories is provided by the Gateway MCP server (https://agent.wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Gateway tool call.

Deterministic rules across all 42 Gateway tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.