search-notion
AI agents call search-notion to retrieve information from Notion MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search tools retrieve and query data without modifying state, fitting the Read category. Severity is medium because search could expose sensitive information in Notion workspaces if the LLM has broad access permissions. Confidence is 0.85 rather than higher because the tool description is empty, requiring inference from the tool name and server capabilities alone.
From the tool's definition Tool name 'search-notion' indicates a search operation against Notion workspace data. Server description confirms it provides 'searching, retrieving' capabilities as core Read operations.
Attacks that exploit this kind of access
search-notion. It is categorised as a Read tool in the Notion MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Notion MCP Server 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 MCP Server. 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 MCP server (sahmadumass/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 →