AI agents call get_bucket_location to retrieve information from Storage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves bucket configuration metadata (location and storage class). It has no side effects, does not modify data, execute commands, or create financial obligations. It is a straightforward informational query with minimal blast radius if misused by an agent.
From the tool's definition Tool name 'get_bucket_location' and description 'Gets the location and storage class of a bucket' indicate a read-only query operation that retrieves metadata about a GCS bucket without modifying or deleting any data.
Attacks that exploit this kind of access
Gets the location and storage class of a bucket. It is categorised as a Read tool in the Storage MCP Server, which means it retrieves data without modifying state.
Register the Storage MCP server in PolicyLayer and add a rule for get_bucket_location: 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.
get_bucket_location 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 get_bucket_location 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 get_bucket_location. 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.
get_bucket_location 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.