AI agents call list_memories to retrieve information from Hi-AI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though list_memories only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
저장된 메모리 목록을 조회합니다. 카테고리별 필터링 가능. 키워드: 뭐 있었지, 저장된 거, 목록, what did I save, list memories, show saved 💡 세션 시작 시 전체 컨텍스트가 필요하면 get_session_context를 사용하세요. It is categorised as a Read tool in the Hi-AI MCP Server, which means it retrieves data without modifying state.
Register the Hi-AI MCP server in PolicyLayer and add a rule for list_memories: 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 Hi-AI. Nothing to install.
list_memories 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 list_memories 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 list_memories. 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.
list_memories is provided by the Hi-AI MCP server (su-record/hi-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.