AI agents use create_bucket to create or update resources in Gcp Storage — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gcp Storage environment.
Creating a bucket is a reversible Write operation—the bucket and its configuration can be modified or deleted later. It modifies cloud infrastructure state by adding a new storage resource. Severity is medium because while bucket creation itself is not destructive, it commits cloud resources and incurs potential costs, and misconfiguration could expose data.
From the tool's definition Tool name: 'create_bucket'; description: 'Create a new GCS bucket.' This creates a new cloud storage resource.
Documented attack patterns abuse exactly the kind of access create_bucket gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gcp Storage, and nothing reaches the server without passing your rules. This is the rule we recommend for create_bucket:
{
"version": "1",
"default": "deny",
"tools": {
"create_bucket": {
"limits": [
{
"counter": "create_bucket_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_bucket stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new GCS bucket. It is categorised as a Write tool in the Gcp Storage MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gcp Storage MCP server in PolicyLayer and add a rule for 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 Gcp Storage. Nothing to install.
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 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 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.
create_bucket is provided by the Gcp Storage MCP server (uysalserkan/gcp-storage-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gcp Storage, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
23 Gcp Storage tools catalogued and risk-classified — across an index of 43,000+ MCP servers.