Terminate an instance.
AI agents call terminate_instance to permanently remove resources in OCI MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Terminating a cloud compute instance permanently destroys it along with any locally-attached ephemeral storage. This cannot be undone, making it clearly Destructive. The blast radius is critical because an AI agent misusing this tool could destroy production workloads, leading to significant downtime and data loss.
From the tool's definition 'Terminate an instance' — terminating a compute instance is an irreversible action that destroys the VM and its ephemeral resources.
Attacks that exploit this kind of access
Terminate an instance. It is categorised as a Destructive tool in the OCI MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the OCI MCP Server MCP server in PolicyLayer and add a rule for terminate_instance: 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 MCP Server. Nothing to install.
terminate_instance is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the terminate_instance 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 terminate_instance. 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.
terminate_instance is provided by the OCI MCP Server MCP server (sarthak-pansare/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 →