AI agents call list_objects 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 queries object metadata from GCS without modifying or deleting data. It is a pure read operation with no side effects, fitting the Read category. Severity is low because listing objects reveals file names and structure but typically exposes only metadata that is already accessible within the bucket's permission scope.
From the tool's definition Tool name 'list_objects' and description explicitly states it 'Lists the names of objects' with filtering/pagination support. No create, modify, or delete operations are described.
Attacks that exploit this kind of access
Lists the names of objects in a Google Cloud Storage (GCS) bucket. Supports filtering by prefix, directory-like listing with a delimiter, pagination, and listing object versions. 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_objects: 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_objects 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_objects 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_objects. 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_objects 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.