AI agents invoke open_note_preview to trigger actions in Anki. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation (opening Anki Browser preview), which is an Execute-category action. It doesn't read/return data to the caller, write/modify data, or perform destructive/financial operations. The blast radius is low since it only opens a UI preview window for human review.
From the tool's definition 'Open the existing note in Anki Browser preview' — triggers an external UI action in the Anki application
Attacks that exploit this kind of access
Open the existing note in Anki Browser preview for human review. It is categorised as a Execute tool in the Anki MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Anki MCP server in PolicyLayer and add a rule for open_note_preview: 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.
open_note_preview is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open_note_preview 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 open_note_preview. 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.
open_note_preview 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 →