AI agents call memento_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.
The tool only performs diagnostic queries to report on system health and status. No data is modified, created, deleted, or used to execute external operations. This is a pure read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'memento_health' and description indicate 'System diagnostics' with actions limited to 'status (quick overview)' and 'health (full report)' — both read-only queries that retrieve information about system state without modification, creation, or…
Attacks that exploit this kind of access
System diagnostics. Actions: status (quick overview), health (full report),. 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_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_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_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_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_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 →