AI agents use upsert_note_type 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 or modifies note type definitions in Anki, which is characteristic of Write operations. It does not delete data (ruling out Destructive), does not execute arbitrary code (ruling out Execute), and the dry-run default and additive-safe constraints mitigate the risk from accidental misuse.
From the tool's definition 'Create or update a note type' - creates or modifies data reversibly. The description explicitly states 'Dry-run by default' and 'additive-safe constraints', indicating modifications are reversible and preview-able.
Attacks that exploit this kind of access
Dry-run by default. Create or update a note type with additive-safe constraints. 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 upsert_note_type: 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.
upsert_note_type 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 upsert_note_type 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 upsert_note_type. 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.
upsert_note_type 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 →