AI agents use memory_restore to create or update resources in Loom — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Loom environment.
The tool creates/modifies memory state by restoring archived memories and clearing archives. While it does not permanently delete (the archive is cleared but the memory is restored to active set), it irreversibly alters the archive structure and reorganizes persistent agent state.
From the tool's definition Tool performs 'Restore a previously archived memory to the active set. Clears the archive' — this modifies the active memory state by moving archived data and clearing the archive, constituting reversible state changes.
Attacks that exploit this kind of access
Restore a previously archived memory to the active set. Clears the archive. It is categorised as a Write tool in the Loom MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Loom MCP server in PolicyLayer and add a rule for memory_restore: 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 Loom. Nothing to install.
memory_restore 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_restore 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_restore. 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_restore is provided by the Loom MCP server (jbarket/loom). 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 →