AI agents call query_database 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.
Querying a database with filters and sorting is a classic Read operation: it retrieves or searches data with no side effects. Even though filters and sorting parameters are involved, they are used to shape what data is returned, not to create, modify, or delete content. The low severity reflects that misuse would only expose unintended data, not cause irreversible harm or financial impact.
From the tool's definition Tool is described as 'Query a database with filters and sorting' — a read-only operation that retrieves data without modifying it. The action 'query' is explicitly retrieval-focused.
Attacks that exploit this kind of access
Query a database with filters and sorting. 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 query_database: 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.
query_database 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 query_database 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 query_database. 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.
query_database 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 →