AI agents call recall_facts to retrieve information from Memoraeu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries stored facts based on a subject parameter. It is a read-only operation that does not create, modify, delete, or execute external actions. The verb 'recall' and 'retrieves' (récupère) confirm this is data retrieval. Even in a zero-knowledge encrypted memory system, recall is fundamentally a Read operation.
From the tool's definition Tool name is 'recall_facts' and description states 'Récupère les faits structurés actifs pour un sujet donné' (Retrieves structured active facts for a given subject). This is a retrieval/query operation with no side effects.
Attacks that exploit this kind of access
Récupère les faits structurés actifs pour un sujet donné. It is categorised as a Read tool in the Memoraeu MCP Server, which means it retrieves data without modifying state.
Register the Memoraeu MCP server in PolicyLayer and add a rule for recall_facts: 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 Memoraeu. Nothing to install.
recall_facts 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 recall_facts 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 recall_facts. 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.
recall_facts is provided by the Memoraeu MCP server (pquattro/memoraeu-mcp). 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 →