AI agents call get_learning_stats to retrieve information from Learnlog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes pre-computed learning metrics from local session history. It is a read-only query operation with no side effects—it does not create, modify, delete, or execute any external actions. The local scope and analytical nature pose minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_learning_stats' and description indicate retrieval of learning statistics and analysis data ('조회합니다' = 'retrieve/query', 'confirm' question type distribution and learning depth scores).
Attacks that exploit this kind of access
특정 날짜의 학습 통계를 조회합니다. 질문 타입별 분포, 학습 깊이 점수를 확인할 수 있습니다. It is categorised as a Read tool in the Learnlog MCP Server, which means it retrieves data without modifying state.
Register the Learnlog MCP server in PolicyLayer and add a rule for get_learning_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 Learnlog. Nothing to install.
get_learning_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 get_learning_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 get_learning_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.
get_learning_stats is provided by the Learnlog MCP server (yujaeyun/learnlog-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_learning_stats is one line of Learnlog's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →