Retrieve a file upload by ID.
AI agents call retrieve_file_upload 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 queries and returns file upload metadata or status by ID without altering state, creating side effects, or exposing sensitive financial data. The 'retrieve' operation is a straightforward read. Severity is low because retrieving file metadata poses minimal risk even if misused by an agent — it only accesses information the agent's Notion token already permits.
From the tool's definition Tool name and description: 'Retrieve a file upload by ID' — the verb 'retrieve' indicates data retrieval with no modification or deletion.
Attacks that exploit this kind of access
Retrieve a file upload by ID. 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 retrieve_file_upload: 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.
retrieve_file_upload 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 retrieve_file_upload 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 retrieve_file_upload. 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.
retrieve_file_upload is provided by the Notion MCP Server MCP server (lrgex/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 →