AI agents call memory_audit 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 is a Read operation - it queries and retrieves flagged memories for audit purposes without modifying, deleting, or executing any operations. The severity is low because while poisoning detection is important, the tool itself only surfaces information for human review without autonomous action. Confidence is high because the verb 'review' and 'returns' clearly indicate read-only inspection.
From the tool's definition Tool 'memory_audit' reviews and returns memories flagged for manual inspection. Keywords: 'Review', 'Returns' indicate data retrieval with no modification. The description emphasizes inspection and flagging for external action rather than performing changes.
Attacks that exploit this kind of access
Review low-trust memories (trust_score < threshold). Returns memories flagged by the poisoning detection heuristic for manual review. 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_audit: 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_audit 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_audit 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_audit. 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_audit 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 →