Restore memories from a backup JSON file.
AI agents use restore to create or update resources in Nexus Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nexus Memory environment.
Restoring from backup is a Write operation because it creates or modifies data (memories) in a reversible manner. It's not Destructive because the original backup persists and the operation can be undone via another backup/restore cycle.
From the tool's definition Tool 'restore' loads and applies memories from a backup JSON file, which modifies the agent's persistent memory state. Description indicates it writes/overwrites memory data from an external source.
Attacks that exploit this kind of access
Restore memories from a backup JSON file. It is categorised as a Write tool in the Nexus Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nexus Memory MCP server in PolicyLayer and add a rule for 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 Nexus Memory. Nothing to install.
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 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 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.
restore is provided by the Nexus Memory MCP server (neboy72/nexus-memory). 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 →