메모리 시스템 통계를 조회합니다.
AI agents call get_memory_stats to retrieve information from Claude Session Continuity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves memory statistics—a read-only operation with no side effects. It queries existing system data without creating, modifying, executing, deleting, or transferring resources. The low severity reflects minimal blast radius if misused by an AI agent, as it only exposes performance metrics.
From the tool's definition Tool name 'get_memory_stats' and description '메모리 시스템 통계를 조회합니다' (retrieve memory system statistics) indicate a query operation that retrieves system metrics without modifying or executing external operations.
Attacks that exploit this kind of access
메모리 시스템 통계를 조회합니다. It is categorised as a Read tool in the Claude Session Continuity MCP Server, which means it retrieves data without modifying state.
Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for get_memory_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 Claude Session Continuity. Nothing to install.
get_memory_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_memory_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_memory_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_memory_stats is provided by the Claude Session Continuity MCP server (leesgit/claude-session-continuity-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 →