What is damens_mcps pfsense-mcp.instructions.md?

An MCP server that lets AI assistants manage pfSense firewalls, which are devices that control network traffic. It runs as an HTTP service and supports API-key or username/password access.

Creating and validating firewall rules, managing pfSense settings, and connecting an AI assistant to a pfSense server.

It gives an assistant a way to perform firewall and network-management tasks programmatically. Strict rule checks help reduce mistakes in security-sensitive changes.

damens_mcps pfsense-mcp.instructions.md — Instructions file for GitHub Copilot by filthyrake: An MCP server that lets AI assistants manage p

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/filthyrake/damens_mcps/pfsense-mcp

Clone the repo

git clone --depth 1 https://github.com/filthyrake/damens_mcps

Made for: GitHub Copilot.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/filthyrake/damens_mcps/pfsense-mcp.svg)](https://agentmods.dev/instructions/filthyrake/damens_mcps/pfsense-mcp)

Your own site

<a href="https://agentmods.dev/instructions/filthyrake/damens_mcps/pfsense-mcp"><img src="https://agentmods.dev/badge/instructions/filthyrake/damens_mcps/pfsense-mcp.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,394 This file is loaded in full into every session.

When invoked 1,394 The same file — it is already loaded in full.

Security scan B 2 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.01394	$0.01394
Opus 5	$0.00697	$0.00697
Sonnet 5	$0.00279	$0.00279
Haiku 4.5	$0.00139	$0.00139

Measured 4d ago against content hash 17c87cae720c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

damens_mcps pfsense-mcp.instructions.md scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Set appropriate permissions: `chmod 600 .env`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8000/health

.github/instructions/pfsense-mcp.instructions.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Path-Specific Instructions: pfSense MCP Server

Path: pfsense-mcp/

Project Overview

The pfSense MCP server provides firewall and network management capabilities through the Model Context Protocol. It allows AI assistants to manage pfSense firewalls programmatically.

Key Characteristics

Architecture: MCP Library-Based (uses official mcp Python library)
Transport: HTTP server with FastAPI
Canonical Server: src/http_pfsense_server.py
Configuration: Environment variables via .env file

Critical Requirements

Server Implementation

ONLY use src/http_pfsense_server.py as the canonical implementation
Do not modify or use other server files (legacy files may exist)
Server uses FastAPI for HTTP transport
Authentication via API keys (preferred) or username/password

Firewall Rule Validation

Firewall rules are security-critical and require thorough validation:

# Required fields for firewall rules
required_fields = ["type", "interface", "protocol", "src", "dst"]

# Valid rule types
valid_types = ["pass", "block", "reject"]

# Rule order matters - validate dependencies

Dangerous Operations

These operations can disrupt network connectivity:

Creating/modifying firewall rules (can block access)
Deleting firewall rules (can open security holes)
Changing interface configurations (can lose connectivity)
Modifying NAT rules (can break port forwarding)

Always validate thoroughly and log changes.

Configuration

Environment Variables

# Required
PFSENSE_HOST=192.168.1.1          # pfSense hostname or IP
PFSENSE_API_KEY=your-api-key      # API key (preferred)
# OR
PFSENSE_USERNAME=admin
PFSENSE_PASSWORD=your-password

# Optional
PFSENSE_PORT=443                  # API port (default: 443)
SSL_VERIFY=true                   # Verify SSL certificates
API_TIMEOUT=30                    # Request timeout in seconds

Configuration File Location

Primary: .env file in pfsense-mcp/ directory
Example: env.example (copy to .env)
NEVER commit .env file

Read the full file on GitHub · 230 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago First seen · 230 lines · 1,394 tokens per session scan B 17c87cae720c

Subscribe to this mod's changes

damens_mcps pfsense-mcp.instructions.md is an instructions file published in the GitHub repository filthyrake/damens_mcps (2 stars, last pushed 3d ago), licensed MIT. It adds 1,394 tokens to every session, about $0.0070 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Planning idrac mcp-server pfsense proxmox-ve truenas-scale

damens_mcps pfsense-mcp.instructions.md