Delete a memory by its key
AI agents call forget to permanently remove resources in Tages — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes stored memory entries from the codebase context system. Once deleted, the memory cannot be recovered without manual re-entry. Although the blast radius is scoped to project memory (not production data or financial systems), the irreversible nature and potential to corrupt the AI agent's understanding of the codebase by removing critical architectural decisions or naming conventions…
From the tool's definition Tool name is 'forget' with description 'Delete a memory by its key' — the verb 'Delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a memory by its key. It is categorised as a Destructive tool in the Tages MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tages MCP server in PolicyLayer and add a rule for 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 Tages. Nothing to install.
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 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 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.
forget is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →