AI agents call list_service_accounts to retrieve information from Gcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates service accounts from a GCP project. While it is a read-only operation (no data is modified or deleted), the sensitivity is elevated to medium severity because service accounts are security-critical resources—their names and metadata could be used to identify attack surface or privilege escalation vectors.
From the tool's definition Tool name is 'list_service_accounts' with description 'List IAM service accounts in a project.' The verb 'list' and action of retrieving/querying service account information with no modification capability indicates a read operation.
Attacks that exploit this kind of access
List IAM service accounts in a project. It is categorised as a Read tool in the Gcp MCP Server, which means it retrieves data without modifying state.
Register the Gcp MCP server in PolicyLayer and add a rule for list_service_accounts: 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 Gcp. Nothing to install.
list_service_accounts 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_service_accounts 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_service_accounts. 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_service_accounts is provided by the Gcp MCP server (lokimcpuniverse/gcp-mcp-server). 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 →