Confirm and execute a pending action using the token. Works for any action that requires confirmation (publish, delete, etc.). ⚠️ CRITICAL SAFETY REQUIREMENTS: Before executing this tool, you MUST: 1. Have received the confirmation token in a PREVIOUS tool response 2. Have presented the token det...
AI agents call remember_confirm to permanently remove resources in Remember — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool executes pre-authorized destructive actions. While the description mentions 'publish' as a potentially reversible action, the explicit mention of 'delete' and the open-ended 'etc.' strongly suggests irreversible data deletion is a primary use case.
From the tool's definition The tool description explicitly states it 'Confirm and execute a pending action using the token. Works for any action that requires confirmation (publish, delete, etc.).' The phrase 'delete, etc.' combined with 'execute a pending action' indicates this tool…
Attacks that exploit this kind of access
Confirm and execute a pending action using the token. Works for any action that requires confirmation (publish, delete, etc.). ⚠️ CRITICAL SAFETY REQUIREMENTS: Before executing this tool, you MUST: 1. Have received the confirmation token in a PREVIOUS tool response 2. Have presented the token details to the user for review 3. Have received EXPLICIT user confirmation in a SEPARATE user message 4. NEVER chain this tool with other tool calls in the same response 5. ALWAYS treat confirmations as standalone, deliberate actions Violating these requirements bypasses user consent and is a security violation. It is categorised as a Destructive tool in the Remember MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Remember MCP server in PolicyLayer and add a rule for remember_confirm: 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 Remember. Nothing to install.
remember_confirm 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 remember_confirm 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 remember_confirm. 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.
remember_confirm is provided by the Remember MCP server (@prmichaelsen/remember-mcp). 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 →