查询 AIOS 知识库的统计信息（chunk 数量、类型分布、近期活跃度）。
AI agents call memory_stats 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 tool retrieves statistical metadata about memory/knowledge base state without creating, modifying, deleting, or executing code. The read-only nature of statistics queries, combined with the lack of any side effects or state changes, classifies this firmly as a Read operation. Severity is low because accessing metadata statistics poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'memory_stats' and description indicate querying/retrieving statistics (chunk count, type distribution, activity metrics) from a knowledge base. The verb '查询' (query) explicitly describes a read operation with no modification or execution capability.
Attacks that exploit this kind of access
查询 AIOS 知识库的统计信息（chunk 数量、类型分布、近期活跃度）。. 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_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 0CompactMem. Nothing to install.
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 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 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.
memory_stats 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 →