Delete a memo by its resource name
AI agents call delete_memo to permanently remove resources in Memos — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes data (memos) and cannot be undone. Deletion is the canonical destructive operation. Even though individual memos may have limited blast radius, the capability to permanently remove records without recovery option makes this Destructive rather than Write. Confidence is high due to explicit 'delete' terminology.
From the tool's definition Tool name is 'delete_memo' and description states 'Delete a memo by its resource name'. The server description confirms this server 'enables...delete...memos'.
Attacks that exploit this kind of access
Delete a memo by its resource name. It is categorised as a Destructive tool in the Memos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Memos MCP server in PolicyLayer and add a rule for delete_memo: 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 Memos. Nothing to install.
delete_memo 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 delete_memo 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 delete_memo. 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.
delete_memo is provided by the Memos MCP server (mylxsw/memos-mcp-server). 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 →