AI agents call memento_system_health 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 tool queries and returns system diagnostics and monitoring information (memory stats, knowledge graph health, consolidation metrics) without modifying, deleting, executing external operations, or affecting the system's state. It is a read-only diagnostic operation. The [DEPRECATED] status does not change its classification.
From the tool's definition Tool name 'memento_system_health' and description 'Get a comprehensive health report' indicate retrieval of diagnostic statistics and metrics with no side effects. Keywords: 'get', 'health report', 'stats', 'metrics'.
Attacks that exploit this kind of access
[DEPRECATED] Get a comprehensive health report for the Memento memory system — memory stats, KG health, consolidation and extraction metrics. 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_system_health: 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_system_health 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_system_health 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_system_health. 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_system_health 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 →