pfsense_firewall_apply · Pfsense MCP: Risk & Policy

WHAT IT DOES

What pfsense_firewall_apply does on Pfsense

AI agents invoke pfsense_firewall_apply to trigger actions in Pfsense. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why pfsense_firewall_apply needs a policy

This tool applies pending firewall configuration changes to the live pfSense firewall. It is an Execute-category action because it triggers an external operation (activating firewall rules) whose effects depend on what changes are queued. Misuse could expose or block network traffic at the firewall level, making severity high.

From the tool's definition POST /api/v2/firewall/apply — 'apply' indicates triggering/activating pending firewall rule changes on the pfSense system

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pfsense_firewall_apply Rate-limited

pfsense_firewall_apply stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pfsense_firewall_apply": {
      "limits": [
        {
          "counter": "pfsense_firewall_apply_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Pfsense, so you can run agents against it safely.

FAQ

Questions about pfsense_firewall_apply

What does the pfsense_firewall_apply tool do? +

POST /api/v2/firewall/apply. It is categorised as a Execute tool in the Pfsense MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pfsense_firewall_apply? +

Register the Pfsense MCP server in PolicyLayer and add a rule for pfsense_firewall_apply: 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.

What risk level is pfsense_firewall_apply? +

pfsense_firewall_apply is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit pfsense_firewall_apply? +

Yes. Add a rate_limit block to the pfsense_firewall_apply 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.

How do I block pfsense_firewall_apply completely? +

Set action: deny in the PolicyLayer policy for pfsense_firewall_apply. 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.

What MCP server provides pfsense_firewall_apply? +

pfsense_firewall_apply 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.