Create a new Cloud Storage bucket
AI agents use storage_create_bucket to create or update resources in Google Cloud — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Cloud environment.
This tool creates a new Google Cloud Storage bucket, which is a reversible write operation. While bucket creation can incur costs and consume quota, the operation itself is not destructive (buckets can be deleted) and does not directly move money.
From the tool's definition Tool name 'storage_create_bucket' and description 'Create a new Cloud Storage bucket' indicate creation of a new cloud resource.
Attacks that exploit this kind of access
Create a new Cloud Storage bucket. It is categorised as a Write tool in the Google Cloud MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Cloud MCP server in PolicyLayer and add a rule for storage_create_bucket: 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 Cloud. Nothing to install.
storage_create_bucket 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 storage_create_bucket 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 storage_create_bucket. 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.
storage_create_bucket is provided by the Google Cloud MCP server (lockon-n/google-cloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
storage_create_bucket is one line of Google Cloud's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →