POST /api/v2/diagnostics/halt_system
AI agents call pfsense_post_diagnostics_halt_system to permanently remove resources in Pfsense — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Halting a firewall system is effectively irreversible via remote means: once the system is halted, the API is no longer reachable, and all network traffic through the firewall stops. This constitutes a critical destructive action with maximum blast radius — it can take down an entire network by disabling the firewall/router.
From the tool's definition 'halt_system' — halts the pfSense firewall system entirely, which is irreversible in the sense that it takes down network infrastructure and cannot be undone remotely once the system is offline
Attacks that exploit this kind of access
POST /api/v2/diagnostics/halt_system. It is categorised as a Destructive tool in the Pfsense MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pfsense MCP server in PolicyLayer and add a rule for pfsense_post_diagnostics_halt_system: 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 Pfsense. Nothing to install.
pfsense_post_diagnostics_halt_system 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 pfsense_post_diagnostics_halt_system 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 pfsense_post_diagnostics_halt_system. 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.
pfsense_post_diagnostics_halt_system is provided by the Pfsense MCP server (abl030/pfsense-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 →