AI agents call search_notion to retrieve information from Notion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query-like operation that retrieves matching pages and databases from a Notion workspace. It has no side effects—it does not create, modify, delete, or execute any operations. The keyword-based search is a read-only operation typical of information retrieval tools. Low severity reflects minimal blast radius if misused by an AI agent, as search alone cannot damage or alter data.
From the tool's definition Tool description explicitly states 'Search Notion for pages and databases by keyword.' Search operations retrieve data without modification.
Attacks that exploit this kind of access
Search Notion for pages and databases by keyword. It is categorised as a Read tool in the Notion MCP Server, which means it retrieves data without modifying state.
Register the Notion MCP server in PolicyLayer and add a rule for search_notion: 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.
search_notion 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 search_notion 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 search_notion. 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.
search_notion 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 →