AI agents call list_instances to retrieve information from Oci without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query of compute instance metadata within OCI. It retrieves data for inspection only, with no capability to create, modify, delete, or execute code. The operation is non-destructive and carries minimal risk even if misused by an AI agent, as the worst outcome would be information disclosure of instances the user already has access to.
From the tool's definition Tool name 'list_instances' and description 'List compute instances in a compartment' indicate a query operation that retrieves information about existing compute instances without modification or side effects.
Attacks that exploit this kind of access
List compute instances in a compartment. It is categorised as a Read tool in the Oci MCP Server, which means it retrieves data without modifying state.
Register the Oci MCP server in PolicyLayer and add a rule for 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 Oci. Nothing to install.
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 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 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.
list_instances is provided by the Oci MCP server (sauryadas/oci-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 →