AI agents use memory_archive to create or update resources in Mementos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mementos environment.
Archiving is a write operation that changes metadata/visibility of stored data without permanent deletion. While the memory is hidden from normal lists, the operation is reversible (memories can typically be unarchived), making it Write rather than Destructive. The medium severity reflects that an agent could archive important memories unintentionally, affecting visibility and retrieval, but data remains recoverable.
From the tool's definition Tool performs 'Archive a memory' operation which modifies data state by hiding from lists while retaining history—a reversible state change typical of archival operations.
Attacks that exploit this kind of access
Archive a memory by ID or key (hides from lists, keeps history). No version needed. It is categorised as a Write tool in the Mementos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mementos MCP server in PolicyLayer and add a rule for memory_archive: 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_archive 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 memory_archive 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_archive. 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_archive 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 →