AI agents call gcloud_list_secrets to retrieve information from Gcloud 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 metadata about secrets without exposing their actual values. It has no side effects, does not modify data, and poses minimal risk since secret names and metadata are generally less sensitive than the secrets themselves. Classified as Read with low severity.
From the tool's definition Tool description explicitly states it lists 'secret names (NOT values)' and shows 'secret name, creation time, and replication policy' — metadata only, no sensitive values retrieved.
Attacks that exploit this kind of access
List Secret Manager secret names (NOT values) in a project. Shows secret name, creation time, and replication policy. It is categorised as a Read tool in the Gcloud MCP Server, which means it retrieves data without modifying state.
Register the Gcloud MCP server in PolicyLayer and add a rule for gcloud_list_secrets: 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 Gcloud. Nothing to install.
gcloud_list_secrets 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 gcloud_list_secrets 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 gcloud_list_secrets. 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.
gcloud_list_secrets is provided by the Gcloud MCP server (prmichaelsen/gcloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →