AI agents call memento_get_predictive_cache_stats 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 retrieves cache statistics and performance metrics without modifying state, executing code, or triggering external operations. It is a pure data retrieval operation with no blast radius if misused by an AI agent. The deprecation status confirms it poses minimal risk.
From the tool's definition Tool name includes 'get' and description explicitly states 'Get predictive cache statistics' with informational metrics (hit rate, cache size, TTL info). No data modification, deletion, or side effects indicated.
Attacks that exploit this kind of access
[DEPRECATED] Get predictive cache statistics — hit rate, cache size, and TTL info. 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_predictive_cache_stats: 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_predictive_cache_stats 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_predictive_cache_stats 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_predictive_cache_stats. 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_predictive_cache_stats 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 →