AI agents call memory_tool_insights 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 retrieves statistical information, past lessons, and recommendations from a memory system. It performs a read-only query operation with no side effects, no code execution, no data modification, and no irreversible actions. The explicit verb 'Get' combined with 'usage stats' and 'lessons learned' indicates a retrieval/query function typical of Read category tools.
From the tool's definition Tool description: 'Get usage stats, lessons learned, and recommendations' - retrieves and queries historical data and analytics about tool usage patterns without modifying or executing any operations.
Attacks that exploit this kind of access
Get usage stats, lessons learned, and recommendations for MCP tools. Helps agents avoid past mistakes and reuse successful patterns. 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_tool_insights: 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_tool_insights 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_tool_insights 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_tool_insights. 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_tool_insights 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 →