Search the connected Notion workspace for pages matching a query. Risk: read.
AI agents call notion_search to retrieve information from Notion MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from Notion without side effects. It matches the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch)'. The low severity reflects minimal blast radius—a misused search can only expose information the agent already has access to.
From the tool's definition Tool name 'notion_search' and description explicitly states 'Search the connected Notion workspace for pages matching a query' with risk marked as 'read'. No modification, deletion, or execution occurs.
Attacks that exploit this kind of access
Search the connected Notion workspace for pages matching a query. Risk: read. It is categorised as a Read tool in the Notion MCP MCP Server, which means it retrieves data without modifying state.
Register the Notion MCP server in PolicyLayer and add a rule for notion_search: 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 MCP. Nothing to install.
notion_search 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_search 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_search. 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_search is provided by the Notion MCP server (limelight-management-group/notion-mcp). 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 →