AI agents call read_object_content 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 data from Google Cloud Storage without modifying, deleting, or executing anything. It is a straightforward read operation that queries object content. The low severity reflects that reading data alone poses minimal risk unless the data itself is sensitive (which is a data classification issue, not a tool capability issue).
From the tool's definition Tool name 'read_object_content' and description 'Reads the content of a specific object' indicate a retrieval operation with no side effects on the object or system state.
Attacks that exploit this kind of access
Reads the content of 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_content: 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_content 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_content 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_content. 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_content 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.