Delete a deck and optionally its cards
AI agents call delete_deck to permanently remove resources in Anki MCP Data Bridge — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes deck data and potentially associated cards from Anki, which cannot be undone. This is irreversible data loss, placing it squarely in the Destructive category. The high severity reflects that an AI agent misusing this could destroy a user's entire study collection without recovery options.
From the tool's definition Tool name is 'delete_deck' and description states 'Delete a deck and optionally its cards' — using the verb 'Delete' which explicitly indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a deck and optionally its cards. It is categorised as a Destructive tool in the Anki MCP Data Bridge MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Anki MCP Data Bridge MCP server in PolicyLayer and add a rule for delete_deck: 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 Anki MCP Data Bridge. Nothing to install.
delete_deck 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_deck 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_deck. 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_deck is provided by the Anki MCP Data Bridge MCP server (stefanspycher/anki-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 →