批量删除卡片
AI agents call anki_delete_notes to permanently remove resources in TalkToAnki — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes flashcard notes from Anki decks. Deletion is inherently irreversible and represents data loss. While the blast radius is limited to the user's own Anki collection (not system-wide), the permanent nature of the operation and potential for an AI agent to inadvertently delete large numbers of user study materials justifies the 'Destructive' category and 'high' severity.
From the tool's definition Tool name 'anki_delete_notes' combined with description '批量删除卡片' (batch delete cards) indicates irreversible deletion of flashcard data.
Attacks that exploit this kind of access
批量删除卡片. It is categorised as a Destructive tool in the TalkToAnki MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TalkToAnki MCP server in PolicyLayer and add a rule for anki_delete_notes: 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 TalkToAnki. Nothing to install.
anki_delete_notes 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 anki_delete_notes 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 anki_delete_notes. 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.
anki_delete_notes is provided by the TalkToAnki MCP server (muxuuu/talktoanki). 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 →