Move a file to a different folder.
AI agents use drive_move to create or update resources in Gworkspace — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gworkspace environment.
Moving a file changes its organizational state (parent folder) but does not delete or destroy data, making it Write rather than Destructive. The blast radius is medium because an AI agent could relocate critical files into inaccessible folders or disrupt organizational structure, but the action remains reversible—files can be moved back.
From the tool's definition Tool description states 'Move a file to a different folder' - this modifies file location metadata within Google Drive, which is a reversible state change.
Attacks that exploit this kind of access
Move a file to a different folder. It is categorised as a Write tool in the Gworkspace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gworkspace MCP server in PolicyLayer and add a rule for drive_move: 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 Gworkspace. Nothing to install.
drive_move 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 drive_move 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_move. 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_move is provided by the Gworkspace MCP server (leoonic/gworkspace-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 →