Create a new deck or subdeck
AI agents use create_deck to create or update resources in Anki MCP Data Bridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Anki MCP Data Bridge environment.
Creating a new deck is a Write operation because it creates new data with no irreversible consequences or side effects. The blast radius is minimal — a mistakenly created deck can be easily removed. This does not qualify as Destructive (no deletion), Execute (no arbitrary code execution), Financial (no money movement), or Read (actively modifies state).
From the tool's definition Tool name and description: "Create a new deck or subdeck" — this operation creates a new data structure in Anki but does not modify or delete existing data, and the operation is reversible by deleting the deck.
Attacks that exploit this kind of access
Create a new deck or subdeck. It is categorised as a Write tool in the Anki MCP Data Bridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Anki MCP Data Bridge MCP server in PolicyLayer and add a rule for create_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.
create_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 create_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 create_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.
create_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 →