从备忘录中删除标签
AI agents call delete_memo_tag 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 deletes/removes tags from memos, which is an irreversible operation that cannot be undone. Tag deletion modifies memo metadata permanently. While not as severe as deleting entire memos, it still constitutes destructive data modification. Categorized as Destructive rather than Write because the operation removes data rather than creating or reversibly modifying it.
From the tool's definition Tool name 'delete_memo_tag' and description '从备忘录中删除标签' (remove tag from memo) indicates irreversible deletion of tag metadata associated with memos.
Attacks that exploit this kind of access
从备忘录中删除标签. 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_tag: 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_tag 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_tag 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_tag. 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_tag is provided by the Memos MCP server (yuzhi-jiang/memos-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 →