Show memory database statistics.
AI agents call memory_stats to retrieve information from Mcp Recall without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and displays statistical information about the memory database (likely counts, sizes, embedding dimensions, etc.) with no side effects. It performs pure data retrieval similar to 'SELECT COUNT(*) FROM table' operations, making it a Read category tool with low severity since it cannot modify state or cause harm.
From the tool's definition Tool name 'memory_stats' and description 'Show memory database statistics' indicate read-only retrieval of database metadata and statistics without modification or deletion of data.
Attacks that exploit this kind of access
Show memory database statistics. It is categorised as a Read tool in the Mcp Recall MCP Server, which means it retrieves data without modifying state.
Register the Mcp Recall 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 Mcp Recall. 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 Mcp Recall MCP server (jensimogit/mcp-recall). 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 →