AI agents call read_object_metadata 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 metadata about an object in GCS without altering data, executing commands, or causing side effects. It is a read-only operation, making it the lowest severity risk category.
From the tool's definition Tool name 'read_object_metadata' and description 'Reads metadata for a specific object' indicate a retrieval operation with no modification or execution of code.
Attacks that exploit this kind of access
Reads metadata for a specific object. 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 read_object_metadata: 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.
read_object_metadata 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 read_object_metadata 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 read_object_metadata. 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.
read_object_metadata 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.