Get memory system statistics - total, by category, by project.
AI agents call memory_stats to retrieve information from Memory-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports statistics about stored memory without creating, modifying, deleting, or executing operations. It is a pure read operation that provides metadata about the memory system's state. The blast radius of misuse is minimal—at worst an agent could inspect statistics to understand stored data, but cannot alter it or trigger side effects.
From the tool's definition Tool name 'memory_stats' and description 'Get memory system statistics' indicate retrieval of aggregate data about the memory system with no modification or execution of external operations.
Attacks that exploit this kind of access
Get memory system statistics - total, by category, by project. It is categorised as a Read tool in the Memory-MCP MCP Server, which means it retrieves data without modifying state.
Register the 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 Memory-MCP. 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 Memory- MCP server (wb200/memory-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 →