AI agents call list_backups 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 metadata from a backup vault. It performs a query operation that does not create, modify, delete, or execute any code. There is no risk of data loss, execution of arbitrary operations, or financial impact.
From the tool's definition Tool name is 'list_backups' and description states it 'Lists all backups' — a retrieval operation with no side effects. The verb 'Lists' is characteristic of Read operations that query and return data without modification.
Attacks that exploit this kind of access
Lists all backups for a given data source in a backup vault. 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_backups: 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_backups 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_backups 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_backups. 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_backups 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.