AI agents call memento_get_quality_report to retrieve information from Memento without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only diagnostic tool that queries and reports on the internal state of the Memento memory system. It retrieves metrics and analysis (health score, coverage, stale/orphan memory identification) without side effects. The [DEPRECATED] marker slightly reduces confidence but does not change the category.
From the tool's definition Tool name contains 'get' and description states 'Get a full quality report' — retrieves diagnostic information about memory system health, coverage, and state. No modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
[DEPRECATED] Get a full quality report for the Memento memory system — health score, coverage analysis, stale and orphan memories. It is categorised as a Read tool in the Memento MCP Server, which means it retrieves data without modifying state.
Register the Memento MCP server in PolicyLayer and add a rule for memento_get_quality_report: 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 Memento. Nothing to install.
memento_get_quality_report 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 memento_get_quality_report 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 memento_get_quality_report. 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.
memento_get_quality_report is provided by the Memento MCP server (joyciakira/memento). 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 →