获取卡组统计信息
AI agents call anki_get_deck_stats to retrieve information from TalkToAnki without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing deck statistics without creating, modifying, or deleting any data. It has no reversible or irreversible side effects. The operation is read-only and returns analytical information about study progress, fitting squarely within the Read category with low severity due to the absence of any actionable side effects.
From the tool's definition Tool name 'anki_get_deck_stats' and description '获取卡组统计信息' (Get deck statistics information) indicate retrieval of aggregate statistics about a deck with no modification or side effects.
Attacks that exploit this kind of access
获取卡组统计信息. It is categorised as a Read tool in the TalkToAnki MCP Server, which means it retrieves data without modifying state.
Register the TalkToAnki MCP server in PolicyLayer and add a rule for anki_get_deck_stats: 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 TalkToAnki. Nothing to install.
anki_get_deck_stats 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 anki_get_deck_stats 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 anki_get_deck_stats. 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.
anki_get_deck_stats is provided by the TalkToAnki MCP server (muxuuu/talktoanki). 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 →