Group matching rows in a Notion data source by one property and return counts per value.
AI agents call notion_db_group_count to retrieve information from Notion DB MCP Helper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates data from a Notion database without creating, modifying, or deleting any records. It performs a read-only grouping and counting operation, which is the lowest-risk category. No side effects, no data mutation.
From the tool's definition Tool description states it returns 'counts per value' by grouping rows—a retrieval and aggregation operation with no modification.
Attacks that exploit this kind of access
Group matching rows in a Notion data source by one property and return counts per value. It is categorised as a Read tool in the Notion DB MCP Helper MCP Server, which means it retrieves data without modifying state.
Register the Notion DB MCP Helper MCP server in PolicyLayer and add a rule for notion_db_group_count: 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 DB MCP Helper. Nothing to install.
notion_db_group_count 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_db_group_count 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_db_group_count. 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_db_group_count is provided by the Notion DB MCP Helper MCP server (trisetiohidayat/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 →