AI agents use copy_object to create or update resources in Storage — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Storage environment.
The copy_object tool creates or duplicates data within GCS buckets. This is a Write category action because it is reversible (the copied object can be deleted). It is not Execute (no arbitrary code run), not Destructive (copying does not delete originals), and not Financial.
From the tool's definition Tool description states it 'Copies an object from one bucket to another or within the same bucket.' Copy operations create new data or modify bucket contents, which is a reversible write action.
Attacks that exploit this kind of access
Copies an object from one bucket to another or within the same bucket. It is categorised as a Write tool in the Storage MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Storage MCP server in PolicyLayer and add a rule for copy_object: 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 Storage. Nothing to install.
copy_object 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_object 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_object. 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_object is provided by the Storage MCP server (@google-cloud/storage-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.