npg-mcp

npg-mcp

MCP server for NginxProxyGuard that manages proxy hosts, certificates, SSL, security rules, and nginx configuration through 108+ tools.

Category
访问服务器

README

NPG MCP Server

MCP server for NginxProxyGuard (NPG) — manage proxy hosts, certificates, SSL, security rules, and nginx configuration through MCP tools.

Built with FastMCP and httpx.

Features

108+ MCP tools across all NPG API categories:

Category Tools
Auth login, logout, me
Dashboard overview, health, geoip stats
Proxy Hosts list, get, create, update, delete, test, clone, sync, regenerate
Security (per-host) rate limit, bot filter, security headers (+presets), upstream, URI block, fail2ban, challenge/CAPTCHA
Geo Restriction get, create, update, delete (per-host)
Certificates list, get, create, delete, renew
Redirect Hosts list, get, create, update, delete
Access Lists list, get, create, update, delete
DNS Providers list, get, create, update, delete, test
Cloud Providers list, get, create, update, delete
WAF list rules, get hosts/config, disable rules
Exploit Rules list, get, create, update, delete, toggle
Settings global settings, system settings, nginx sync
Logs access logs, audit logs, system logs, stats
Backups list, get, create, delete, restore
API Tokens list, get, create, update, revoke, delete

Quick Start

Prerequisites

  • A running NginxProxyGuard (NPG) instance with API access
  • Docker and Docker Compose (for containerized deployment)
  • Python 3.11+ (for local development)

Local Development

git clone https://github.com/four2mis/npg-mcp.git
cd npg-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .

Create a .env file (copy from .env.example):

cp .env.example .env

Run in stdio mode:

python3 -m npg_mcp.main

Docker Deployment (pre-built)

Pull the image from GitHub Container Registry:

docker pull ghcr.io/four2mis/npg-mcp:latest

Create a .env file from the template:

cp .env.example .env
# then edit .env with your NPG credentials

Or run with Docker Compose using the included docker-compose.yml:

# Pull & run (uses pre-built image)
docker compose up -d

# Or build from source
docker compose up -d --build

The included docker-compose.yml:

services:
  npg-mcp:
    image: ghcr.io/four2mis/npg-mcp:latest
    # build: .  # uncomment to build from source instead
    container_name: npg-mcp
    restart: unless-stopped
    networks:
      - npg-network
    environment:
      - NPG_BASE_URL=http://npg-api:8080
      - NPG_USERNAME=${NPG_USERNAME}
      - NPG_PASSWORD=${NPG_PASSWORD}
      - MCP_PORT=8081
    ports:
      - "8081:8081"

networks:
  npg-network:
    external: true

Hermes MCP Config

mcp_servers:
  npg-mcp:
    url: http://<host>:8081/mcp
    connect_timeout: 30

Authentication

The server auto-authenticates on first use using NPG_USERNAME and NPG_PASSWORD. No manual token management needed — every tool call automatically refreshes auth.

Alternatively, call npg_auth_login directly for explicit authentication.

Environment Variables

Variable Default Description
NPG_BASE_URL http://npg-api:8080 NPG API base URL
NPG_USERNAME NPG login username (required)
NPG_PASSWORD NPG login password (required)
MCP_PORT 8081 MCP server listening port

Project Structure

npg_mcp/
  main.py       # All 108+ MCP tools
  client.py     # HTTP client wrapper with auto-auth
  __init__.py
Dockerfile      # Multi-stage Docker build
docker-compose.yml
pyproject.toml  # Dependencies: mcp>=1.0, httpx>=0.27

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选