List Compute Engine instances
AI agents call compute_list_instances to retrieve information from Google Cloud without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query/list operation on existing Compute Engine instances. It has no capability to create, modify, delete, or execute actions on those instances. The blast radius of misuse is minimal — an attacker gains only visibility into existing infrastructure configuration. This is a straightforward Read category tool.
From the tool's definition Tool name is 'compute_list_instances' and description states 'List Compute Engine instances' — a read-only operation that retrieves instance information without modification or side effects.
Attacks that exploit this kind of access
List Compute Engine instances. It is categorised as a Read tool in the Google Cloud MCP Server, which means it retrieves data without modifying state.
Register the Google Cloud MCP server in PolicyLayer and add a rule for compute_list_instances: 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 Google Cloud. Nothing to install.
compute_list_instances 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 compute_list_instances 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 compute_list_instances. 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.
compute_list_instances is provided by the Google Cloud MCP server (lockon-n/google-cloud-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 →