AI agents call list_backup_vaults 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 retrieves and enumerates backup vault metadata without creating, modifying, deleting, or executing any operations. It is a read-only information retrieval function with minimal blast radius if misused by an AI agent—the worst outcome would be information disclosure of vault names and metadata in the specified project/location.
From the tool's definition Tool name 'list_backup_vaults' and description 'Lists all backup vaults in a given project and location' indicate a query/retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Lists all backup vaults in a given project and location. 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 list_backup_vaults: 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.
list_backup_vaults 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 list_backup_vaults 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 list_backup_vaults. 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.
list_backup_vaults 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.