Retrieve a database in Notion
AI agents call notion_retrieve_database 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.
This tool retrieves or fetches data from a Notion database without modifying, executing operations on external systems, or deleting anything. It is a straightforward read operation. The blast radius is minimal—misuse would at worst allow unauthorized viewing of database contents, not destructive or financial harm.
From the tool's definition Tool name is 'notion_retrieve_database' and description states 'Retrieve a database in Notion'. The verb 'retrieve' indicates a data query operation with no side effects.
Attacks that exploit this kind of access
Retrieve a database in 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 notion_retrieve_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 MCP Server. Nothing to install.
notion_retrieve_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 notion_retrieve_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 notion_retrieve_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.
notion_retrieve_database is provided by the Notion MCP Server MCP server (tkc/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 →