AI agents call list_insights_configs 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 lists configuration metadata from Google Cloud Storage Insights. It performs a read-only query operation that returns information about existing configurations without creating, modifying, deleting, or executing any operations. The blast radius is minimal—at worst, an attacker gains visibility into Storage Insights configurations, which is informational only.
From the tool's definition Tool name 'list_insights_configs' and description 'Lists the names of all Storage Insights dataset configurations' indicate a query/retrieval operation with no data modification or side effects.
Attacks that exploit this kind of access
Lists the names of all Storage Insights dataset configurations for a given project. 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_insights_configs: 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_insights_configs 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_insights_configs 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_insights_configs. 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_insights_configs 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.