AI agents call memory_auto_status to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and reports statistics about an internal queue. It does not modify, delete, or execute any operations. The 'Get' verb and the nature of status monitoring confirm this is a Read category tool with low severity impact.
From the tool's definition Tool name 'memory_auto_status' and description explicitly states it 'Get[s] the current auto-memory extraction queue stats' - a read-only query operation that retrieves status metrics (pending, processing, processed, failed, dropped) with no side effects.
Attacks that exploit this kind of access
Get the current auto-memory extraction queue stats (pending, processing, processed, failed, dropped). It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.
Register the Mementos MCP server in PolicyLayer and add a rule for memory_auto_status: 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 Mementos. Nothing to install.
memory_auto_status 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_auto_status 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_auto_status. 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_auto_status is provided by the Mementos MCP server (@hasna/mementos). 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 →