AI agents use update_page_title 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 creates or modifies data (page title) in a reversible manner, matching the Write category definition. Severity is medium because renaming pages could cause confusion or disruption to workspace organization if misused by an AI agent, but the action can be easily undone without data loss.
From the tool's definition Tool description states 'Rename a Notion page', which modifies existing page metadata. The action is reversible (can be renamed again to restore original title) and does not delete or destroy data.
Attacks that exploit this kind of access
Rename a Notion 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 update_page_title: 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.
update_page_title 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 update_page_title 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 update_page_title. 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.
update_page_title 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 →