AI agents call list_log_entries 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 queries and retrieves log data from Google Cloud Logging without side effects. It falls squarely into the Read category as it merely accesses and returns existing log entries. The severity is low because reading logs does not directly enable data modification, destruction, or financial impact, though logs themselves may contain sensitive information.
From the tool's definition The tool is described as a primary tool to 'search and retrieve log entries' with no mention of modification, deletion, or execution capabilities. The verb 'retrieve' and function of searching logs indicates read-only access.
Attacks that exploit this kind of access
Use this as the primary tool to search and retrieve log entries from Google Cloud Logging. It. 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_log_entries: 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_log_entries 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_log_entries 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_log_entries. 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_log_entries 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.