Find notes matching a query in Anki
AI agents call find-notes to retrieve information from Anki MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from Anki's note storage without side effects. It matches the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch).' The severity is low because even if misused by an agent, it cannot modify state, delete data, or trigger external actions — it only exposes stored information that may already be accessible.
From the tool's definition Tool is described as 'Find notes matching a query in Anki' — a search/retrieval operation with no indication of modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Find notes matching a query in Anki. It is categorised as a Read tool in the Anki MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Anki MCP Server MCP server in PolicyLayer and add a rule for find-notes: 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 Server. Nothing to install.
find-notes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the find-notes 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 find-notes. 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.
find-notes is provided by the Anki MCP Server MCP server (johwiebe/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 →