AI agents use add_notes_batch 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.
This tool creates new note records in bulk, which is a Write operation — it modifies state by adding data but does not irreversibly delete, execute arbitrary code, move money, or perform destructive operations. Severity is medium because bulk creation could cause spam or clutter if misused by an agent, but the effects are reversible through delete operations.
From the tool's definition Tool description states 'Create multiple review-pending notes' — the verb 'Create' indicates data modification. The tool accepts batch input to add notes to an Anki deck via AnkiConnect, which is a reversible write operation (notes can be deleted).
Attacks that exploit this kind of access
Create multiple review-pending notes with stable per-item outcomes. 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 add_notes_batch: 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.
add_notes_batch 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 add_notes_batch 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 add_notes_batch. 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.
add_notes_batch 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 →