AI agents use restore_document to create or update resources in Ai Brain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ai Brain environment.
This tool recreates or modifies the state of a previously deleted document, making it accessible again. While it reverses a prior deletion (rather than creating new data), it is not itself destructive—it is a restorative write operation that changes document metadata/state.
From the tool's definition Tool description states 'Restore a soft-deleted document...back into its space', which reverses a deletion by modifying document state from deleted to active.
Attacks that exploit this kind of access
Restore a soft-deleted document (from list_trash) back into its space. It is categorised as a Write tool in the Ai Brain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ai Brain MCP server in PolicyLayer and add a rule for restore_document: 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 Ai Brain. Nothing to install.
restore_document 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_document 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_document. 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_document is provided by the Ai Brain MCP server (thejoshgriffith/ai-brain). 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 →