AI agents call drive_get_folder_contents to retrieve information from Google without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that retrieves and displays folder contents from Google Drive. It has no side effects—it neither modifies, deletes, nor executes anything. The blast radius is minimal: disclosure of folder structure and file metadata. Even if an AI misuses this tool, the worst outcome is unauthorized information discovery within accessible Drive folders.
From the tool's definition Tool name 'drive_get_folder_contents' and description 'List the contents of a specific Drive folder' indicate a query/retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
List the contents of a specific Drive folder. It is categorised as a Read tool in the Google MCP Server, which means it retrieves data without modifying state.
Register the Google MCP server in PolicyLayer and add a rule for drive_get_folder_contents: 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 Google. Nothing to install.
drive_get_folder_contents 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_get_folder_contents 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_get_folder_contents. 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_get_folder_contents is provided by the Google MCP server (psckeithw/mcp-google). 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 →