AI agents call drive_read_doc to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and exports document content from Google Drive in a specified format. It has no side effects, does not modify data, and does not execute code or commands.
From the tool's definition Tool name is 'drive_read_doc' and description states 'Export a Google Drive file... and return its content' and 'read document contents' — purely retrieval with no modification or deletion.
Attacks that exploit this kind of access
Export a Google Drive file (Doc, Sheet, Slide, etc.) to a specified format and return its content. Defaults to plain text export. Use this to read document contents without opening the Google editor. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for drive_read_doc: 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 Access. Nothing to install.
drive_read_doc 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 drive_read_doc 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 drive_read_doc. 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.
drive_read_doc is provided by the Access MCP server (scottpedia0/access). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
drive_read_doc is one line of Access's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →