AI agents call bucket_exists to retrieve information from Gcp Storage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a simple existence check operation with no mutative effects. It only queries the state of a resource (whether a bucket exists) and returns a boolean result. No data is created, modified, deleted, or at risk of being affected. This is a classic Read operation with minimal blast radius if misused.
From the tool's definition Tool name 'bucket_exists' and description 'Check if a bucket exists' indicate a query operation that retrieves existence status without modifying any data or triggering side effects.
Documented attack patterns abuse exactly the kind of access bucket_exists 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 bucket_exists:
{
"version": "1",
"default": "deny",
"tools": {
"bucket_exists": {}
}
}bucket_exists is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Check if a bucket exists. It is categorised as a Read tool in the Gcp Storage MCP Server, which means it retrieves data without modifying state.
Register the Gcp Storage MCP server in PolicyLayer and add a rule for bucket_exists: 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.
bucket_exists is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the bucket_exists 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 bucket_exists. 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.
bucket_exists 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.