AI agents use restore_page to create or update resources in Notion — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Notion environment.
This tool modifies data by changing a page's archive status, making it a Write operation rather than Read (it changes state) or Destructive (the change is reversible—an archived page can be archived again). The severity is medium because restoring a page could affect workspace organization and visibility, but the impact is localized to a single page and reversible.
From the tool's definition The tool 'restore_page' restores an archived page, which is a reversible modification operation that changes the state of a page from archived to active. The description explicitly states it 'Restore an archived page.'
Attacks that exploit this kind of access
Restore an archived page. It is categorised as a Write tool in the Notion MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Notion MCP server in PolicyLayer and add a rule for restore_page: 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 Notion. Nothing to install.
restore_page 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_page 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_page. 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_page is provided by the Notion MCP server (kuldeepjha5176/notion-mcp-server). 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 →