Terminate an instance and tear down its VCN (subnets, gateways, security lists).
AI agents call teardown_stack 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.
This tool irreversibly deletes multiple cloud resources: a compute instance, VCN, subnets, gateways, and security lists. These deletions cannot be undone and could take down running workloads and network connectivity. The blast radius is critical as it affects an entire network stack and hosted services.
From the tool's definition 'Terminate an instance and tear down its VCN (subnets, gateways, security lists)' — permanently destroys compute instance and all associated networking resources
Attacks that exploit this kind of access
Terminate an instance and tear down its VCN (subnets, gateways, security lists). 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 teardown_stack: 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.
teardown_stack 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 teardown_stack 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 teardown_stack. 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.
teardown_stack 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 →