AI agents use copy_file to create or update resources in Google — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google environment.
The copy_file tool creates new data (a duplicate file) in Google Drive, which is a Write category action. It is reversible (the copy can be deleted), not destructive. Severity is medium because while file duplication itself is not inherently dangerous, an agent could misuse it to spam copies, exhaust storage quota, or create unauthorized duplicates of sensitive documents.
From the tool's definition "Copy any Google Drive file. Optionally rename and/or place in a specific folder." — This tool creates a new file resource by duplicating an existing one, which is a reversible write operation.
Attacks that exploit this kind of access
Copy any Google Drive file. Optionally rename and/or place in a specific folder. It is categorised as a Write tool in the Google MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google MCP server in PolicyLayer and add a rule for copy_file: 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.
copy_file is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the copy_file 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 copy_file. 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.
copy_file is provided by the Google MCP server (ztgluis/google-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 →