io.github.antonio-mello-ai/mcp-pfsense

AI 与智能体

by antonio-mello-ai

通过 AI 助手管理 pfSense 防火墙,支持规则、DHCP、DNS 等配置与运维操作。

什么是 io.github.antonio-mello-ai/mcp-pfsense

通过 AI 助手管理 pfSense 防火墙,支持规则、DHCP、DNS 等配置与运维操作。

README

mcp-pfsense

PyPI Python License: MIT

MCP server for managing pfSense firewalls through AI assistants like Claude, ChatGPT, and Copilot.

Requires: pfrest package installed on your pfSense instance (provides the REST API).

Features

17 tools across 6 categories:

CategoryToolsDescription
Systemget_system_status, get_interfacesVersion, CPU, memory, uptime, temperature, network interfaces
Firewalllist_firewall_rules, add_firewall_rule, delete_firewall_rule, list_firewall_aliasesRule management with interface filtering, alias listing
DHCPlist_dhcp_leases, list_dhcp_static_mappings, add_dhcp_static_mapping, delete_dhcp_static_mappingActive leases, IP reservations
DNSlist_dns_host_overrides, add_dns_host_override, delete_dns_host_overrideUnbound DNS Resolver host overrides
Monitoringget_gateway_status, get_arp_table, list_servicesGateway health, connected devices, service status
Servicesrestart_serviceRestart any pfSense service

Safety

All destructive operations (delete rules, delete mappings, restart services) require two-step confirmation — the tool returns a warning on first call and only executes when called again with confirm=true.

Installation

bash
# Using uvx (recommended)
uvx mcp-pfsense

# Using pip
pip install mcp-pfsense

Prerequisites

  1. pfSense with pfrest package installed
  2. A user account with API access (typically admin)

Configuration

Set environment variables:

VariableRequiredDefaultDescription
PFSENSE_HOSTYespfSense hostname or IP
PFSENSE_PASSWORDYesAPI user password
PFSENSE_USERNAMENoadminAPI username
PFSENSE_PORTNo443API port
PFSENSE_SCHEMENohttpshttp or https
PFSENSE_VERIFY_SSLNofalseVerify SSL certificate

Claude Desktop

Add to claude_desktop_config.json:

json
{
  "mcpServers": {
    "pfsense": {
      "command": "uvx",
      "args": ["mcp-pfsense"],
      "env": {
        "PFSENSE_HOST": "10.10.10.1",
        "PFSENSE_PASSWORD": "your-password"
      }
    }
  }
}

Claude Code

bash
claude mcp add pfsense -- uvx mcp-pfsense

Then set environment variables in your shell or .env file.

Usage Examples

Once connected, ask your AI assistant:

  • "What's the pfSense system status?"
  • "Show me all firewall rules on the LAN interface"
  • "List active DHCP leases"
  • "Add a DNS entry for nas.home.lan pointing to 10.10.10.50"
  • "What devices are connected to the network?" (ARP table)
  • "Show gateway health and latency"
  • "Create a firewall rule to allow TCP port 8080 on LAN"
  • "Reserve IP 10.10.10.60 for MAC aa:bb:cc:dd:ee:20"

API Compatibility

  • pfSense: 2.7.x (tested on 2.7.2)
  • pfrest: v2.x (REST API v2)
  • Python: 3.11+

Note: pfrest runs on nginx (port 80 by default), separate from the pfSense WebGUI (lighttpd on port 443). If your pfrest is configured on a non-standard port, set PFSENSE_PORT and PFSENSE_SCHEME accordingly.

Development

bash
git clone https://github.com/antonio-mello-ai/mcp-pfsense.git
cd mcp-pfsense
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

# Run tests
pytest

# Lint and type check
ruff check .
mypy src/

License

MIT

<!-- mcp-name: io.github.antonio-mello-ai/mcp-pfsense -->

常见问题

io.github.antonio-mello-ai/mcp-pfsense 是什么?

通过 AI 助手管理 pfSense 防火墙,支持规则、DHCP、DNS 等配置与运维操作。

相关 Skills

Claude接口

by anthropics

Universal
热门

面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。

想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心

AI 与智能体
未扫描171.4k

RAG架构师

by alirezarezvani

Universal
热门

聚焦生产级RAG系统设计与优化,覆盖文档切块、检索链路、索引构建、召回评估等关键环节,适合搭建可扩展、高准确率的知识库问答与检索增强应用。

面向RAG落地,把知识库、向量检索和生成链路系统串联起来,做架构设计时更清晰,也更少踩坑。

AI 与智能体
未扫描24.9k

多智能体架构

by alirezarezvani

Universal
热门

聚焦多智能体系统架构设计,梳理 Supervisor、Swarm、分层和 Pipeline 等模式,覆盖角色定义、通信协作与性能评估,适合规划稳健可扩展的 AI agent 编排方案。

帮你系统解决多智能体应用的架构设计与协同编排难题,适合构建复杂 AI 工作流,成熟度高、社区认可也很亮眼。

AI 与智能体
未扫描24.9k

相关 MCP Server

知识图谱记忆

编辑精选

by Anthropic

热门

Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。

帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。

AI 与智能体
89.7k

顺序思维

编辑精选

by Anthropic

热门

Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。

这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。

AI 与智能体
89.2k

by deusdata

热门

持久化的代码库知识图谱,可跨会话保留上下文,在 session 重启或上下文压缩后仍能继续使用。

专治 AI 编程助手“会话失忆”,把代码库沉淀为持久知识图谱,重启或压缩上下文后也能无缝续上开发状态。

AI 与智能体
37.3k

评论