Hook 系统健康检查 — 查看最近 N 小时内哪些 hook 在触发、哪些静默失败。
AI agents call memory_hook_health to retrieve information from 0CompactMem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a diagnostic/monitoring tool that inspects the state of memory hooks and their recent activity. It performs information retrieval only, with no side effects on the system. The blast radius if misused by an AI agent is minimal—an agent could potentially gather debugging information about system internals, but cannot modify or delete data, execute operations, or trigger financial impacts.
From the tool's definition Tool name 'memory_hook_health' and description indicate it 'views' (查看) which hooks are triggering and silently failing within recent N hours.
Attacks that exploit this kind of access
Hook 系统健康检查 — 查看最近 N 小时内哪些 hook 在触发、哪些静默失败。. It is categorised as a Read tool in the 0CompactMem MCP Server, which means it retrieves data without modifying state.
Register the 0CompactMem MCP server in PolicyLayer and add a rule for memory_hook_health: 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 0CompactMem. Nothing to install.
memory_hook_health 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 memory_hook_health 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 memory_hook_health. 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.
memory_hook_health is provided by the 0CompactMem MCP server (soolaugust/0compactmem). 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 →