AI agents use remember_fact to create or update resources in Memoraeu — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memoraeu environment.
This tool writes a structured fact to persistent memory with a time-validity component. It creates new data rather than modifying or deleting existing data, making it a Write operation. Severity is medium because it persists information in a zero-knowledge memory layer, potentially storing sensitive data that could be retrieved later by other tools.
From the tool's definition "Mémorise un fait structuré" (Memorizes a structured fact) with temporal validity — creates/stores new data persistently
Attacks that exploit this kind of access
Mémorise un fait structuré avec validité temporelle. It is categorised as a Write tool in the Memoraeu MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memoraeu MCP server in PolicyLayer and add a rule for remember_fact: 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.
remember_fact is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the remember_fact 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 remember_fact. 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.
remember_fact 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 →