Show statistics about the memory database.
AI agents call memory_stats to retrieve information from Agent Memory 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 the memory database (e.g., record counts, storage usage) with no side effects. It is a read-only query operation. Severity is low because statistics queries have no ability to corrupt, expose sensitive data at scale, or affect system integrity beyond potentially revealing structural information about the database.
From the tool's definition Tool name 'memory_stats' and description 'Show statistics about the memory database' indicate a retrieval operation that queries and returns aggregate information without modifying or deleting data.
Attacks that exploit this kind of access
Show statistics about the memory database. It is categorised as a Read tool in the Agent Memory MCP Server, which means it retrieves data without modifying state.
Register the Agent Memory 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 Agent Memory. 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 Agent Memory MCP server (khaled1174/agent-memory). 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 →