AI agents use set_note_cards_suspended to create or update resources in Anki — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Anki environment.
Suspending/unsuspending cards is a write operation that changes card state reversibly. While it affects card visibility and review scheduling, the underlying data remains intact and the action can be undone by unsuspending. This is less severe than Execute (no code runs) or Destructive (data persists).
From the tool's definition Tool performs 'suspend or unsuspend all cards generated from one note' — a reversible state change operation that modifies card status without permanently deleting or destroying data.
Attacks that exploit this kind of access
Suspend or unsuspend all cards generated from one note. It is categorised as a Write tool in the Anki MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Anki MCP server in PolicyLayer and add a rule for set_note_cards_suspended: 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. Nothing to install.
set_note_cards_suspended is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_note_cards_suspended 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 set_note_cards_suspended. 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.
set_note_cards_suspended is provided by the Anki MCP server (yama662607/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 →