Comprehensive health check for memories. Detects: stale (old + 0 access), high-importance-forgotten (importance>=7 + not accessed in 60d), and possibly-superseded (newer memory with similar key). Returns actionable summary.
AI agents call memory_health 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 performs diagnostic analysis of existing memory data without creating, modifying, deleting, or executing external operations. It is purely observational: it checks for stale memories, forgotten high-importance items, and superseded entries, then reports findings. The 'actionable summary' is guidance for a user/agent to act on, not direct action by the tool itself.
From the tool's definition Tool name 'memory_health' and description 'Comprehensive health check' indicates introspection/monitoring. The description specifies it 'Detects', 'Returns actionable summary' — passive analysis operations.
Attacks that exploit this kind of access
Comprehensive health check for memories. Detects: stale (old + 0 access), high-importance-forgotten (importance>=7 + not accessed in 60d), and possibly-superseded (newer memory with similar key). Returns actionable summary. 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_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 Mementos. Nothing to install.
memory_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 memory_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 memory_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.
memory_health 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 →