AI agents call list_backup_plans 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 plans—a read-only operation. It does not create, modify, delete, execute code, or move money. The blast radius is minimal: exposure reveals which backup plans exist in a project, which is informational data.
From the tool's definition Tool name 'list_backup_plans' and description 'Lists all backup plans in a given project and location' indicate a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
Lists all backup plans 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_plans: 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_plans 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_plans 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_plans. 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_plans 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.