AI agents call find_protectable_resources 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 performs a listing/discovery operation with no side effects. It retrieves metadata about existing resources but does not create, modify, delete, or execute actions. It is purely informational, placing it firmly in the Read category with low severity.
From the tool's definition Tool description states 'Lists protectable resources in a project' — a query operation that retrieves data about Cloud SQL instances, Compute VMs, and Compute Disks without modification, deletion, or execution.
Attacks that exploit this kind of access
Lists protectable resources in a project. This includes Cloud SQL instances, Compute VMs, and Compute Disks. 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 find_protectable_resources: 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.
find_protectable_resources 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 find_protectable_resources 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 find_protectable_resources. 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.
find_protectable_resources 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.