AI agents call memory_recall_deep 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.
memory_recall_deep retrieves stored memory data using search and retrieval mechanisms. It has no side effects on the data (no create, update, delete, or execute operations). Even though it involves multiple parallel search agents, the operation remains fundamentally a read query.
From the tool's definition Tool description explicitly states it performs 'recall' and 'retrieval' operations with 'parallel search agents' — these are read-only query operations with no modification, deletion, or execution of external code.
Attacks that exploit this kind of access
Deep memory recall using ASMR (Agentic Search and Memory Retrieval) — runs 3 parallel search agents (facts, context, temporal) for high-accuracy retrieval with optional ensemble answering. 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_recall_deep: 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_recall_deep 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_recall_deep 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_recall_deep. 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_recall_deep 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 →