AI agents use ensure_deck 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.
The tool creates or initializes a deck, which is data creation but reversible (decks can be deleted). It is explicitly safe and idempotent, meaning repeated calls do not cause unintended side effects. This is a Write operation with low severity because deck creation in Anki is low-risk — it does not execute arbitrary code, delete data, move funds, or cause significant blast radius if misused by an agent.
From the tool's definition Tool description states 'Create a deck if missing' — this creates new data (deck structure) in Anki. The name 'ensure_deck' and description 'Safe and idempotent' indicate reversible creation without destructive side effects.
Attacks that exploit this kind of access
Create a deck if missing. Safe and idempotent. 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 ensure_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. Nothing to install.
ensure_deck 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 ensure_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 ensure_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.
ensure_deck 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 →