Retrieve a page
AI agents call notion_retrieve_page to retrieve information from MCP Notion Server (@suncreation) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries page data from Notion without creating, modifying, or deleting any content. It is a read-only operation with minimal blast radius if misused by an AI agent—at worst, it exposes data the agent is already authorized to access through the Notion workspace permissions.
From the tool's definition Tool name is 'notion_retrieve_page' and description states 'Retrieve a page'. The verb 'retrieve' indicates data retrieval with no modifications or side effects.
Attacks that exploit this kind of access
Retrieve a page. It is categorised as a Read tool in the MCP Notion Server (@suncreation) MCP Server, which means it retrieves data without modifying state.
Register the MCP Notion Server (@suncreation) MCP server in PolicyLayer and add a rule for notion_retrieve_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 MCP Notion Server (@suncreation). Nothing to install.
notion_retrieve_page is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the notion_retrieve_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 notion_retrieve_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.
notion_retrieve_page is provided by the MCP Notion Server (@suncreation) MCP server (suncreation/mcp-notion-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 →