AI agents use upload_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.
This tool creates new data objects in GCS buckets. While reversible (files can be deleted), it modifies the storage state. It's categorized as Write rather than Execute because the primary action is data creation, not command execution.
From the tool's definition Tool uploads a file to a GCS bucket, which creates/adds data to cloud storage. The description explicitly states 'Uploads a file', confirming data creation.
Attacks that exploit this kind of access
Uploads a file to a GCS 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 upload_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.
upload_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 upload_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 upload_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.
upload_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.