Delete an endpoint group
AI agents call delete_endpoint_group to permanently remove resources in ACI MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes an endpoint group (EPG) from a Cisco ACI fabric, which is a destructive operation that cannot be undone without manual recreation. EPGs are critical network policy objects that define application endpoints and their connectivity rules. Deletion causes immediate loss of network segmentation and policy enforcement for affected endpoints, with potential for service disruption.
From the tool's definition Tool name 'delete_endpoint_group' and description 'Delete an endpoint group' indicate irreversible deletion of network infrastructure configuration.
Attacks that exploit this kind of access
Delete an endpoint group. It is categorised as a Destructive tool in the ACI MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ACI MCP Server MCP server in PolicyLayer and add a rule for delete_endpoint_group: 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 ACI MCP Server. Nothing to install.
delete_endpoint_group 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 delete_endpoint_group 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 delete_endpoint_group. 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.
delete_endpoint_group is provided by the ACI MCP Server MCP server (jim-coyne/aci_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 →