AI agents call list_cluster_options 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 queries read-only configuration data (available Kubernetes versions and compute shapes) for the purpose of informing cluster creation decisions. It has no side effects, does not execute code, does not modify resources, and does not incur financial transactions. The blast radius of misuse is minimal—an attacker can only learn what options are available, not provision or access resources.
From the tool's definition Tool name 'list_cluster_options' and description 'List Kubernetes versions and shapes available for new OKE clusters' indicate a query operation that retrieves metadata about available options without modifying or executing infrastructure.
Attacks that exploit this kind of access
List Kubernetes versions and shapes available for new OKE clusters 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_cluster_options: 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_cluster_options 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_cluster_options 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_cluster_options. 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_cluster_options 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 →