NetBox Read/Write MCP Server
A Model Context Protocol server that provides safe, intelligent read/write access to NetBox instances, designed with safety-first principles for Large Language Model automation.
README
NetBox Read/Write MCP Server
A Model Context Protocol (MCP) server that provides safe, intelligent read/write access to NetBox instances. Designed with safety-first principles for Large Language Model automation.
🎯 Project Vision
Create a robust bridge between LLMs and NetBox that enables:
- Safe Write Operations: All mutations require explicit confirmation
- Idempotent Operations: Consistent results regardless of call frequency
- Integration Ready: Designed to be orchestrated by higher-level automation platforms
- Enterprise Grade: Production-ready with comprehensive safety mechanisms
🚧 Development Status
Current Version: v0.1.0-dev (Phase 1: Foundation & Read-Only Core)
This project is under active development. See GitHub Issues for current roadmap and progress.
📋 Roadmap
Development follows a phased approach with safety-first principles:
- v0.1 - Foundation & Read-Only Core (current)
- v0.2 - Initial Write Capabilities & Safety
- v0.3 - Advanced R/W Operations & Relations
- v0.4 - Enterprise Features & Integration-readiness
- v1.0 - Production-readiness & Full Integration
🔧 Development Setup
Prerequisites
- Python 3.9+
- Access to a NetBox instance (Cloud or self-hosted)
- NetBox API token with appropriate permissions
Installation
# Clone the repository
git clone https://github.com/Deployment-Team/netbox-mcp.git
cd netbox-mcp
# Install in development mode
pip install -e .
# Install development dependencies
pip install -e ".[dev]"
Configuration
Copy the example environment file and configure your NetBox instance:
cp .env.example .env
# Edit .env with your NetBox URL and API token
🏗️ Architecture
The server follows a modular design:
netbox_mcp.client: NetBox API client with safety mechanismsnetbox_mcp.server: MCP server with tool definitionsnetbox_mcp.config: Configuration management- Safety Layer: Confirmation parameters and dry-run mode throughout
🔒 Safety Features
CRITICAL: This server can perform write operations on NetBox data.
Built-in Safety Mechanisms:
- Confirmation Required: All write operations require
confirm=True - Dry-Run Mode: Global
NETBOX_DRY_RUN=trueprevents actual writes - Comprehensive Logging: All mutations logged with detailed context
- Idempotent Design: Safe to retry operations
- Error Handling: Graceful failure with clear error messages
📊 Current Implementation Status
✅ Completed:
- Project structure and dependencies
- Exception handling framework
- Configuration foundation
🚧 In Progress:
- NetBox API client (read-only)
- Basic MCP server implementation
📅 Upcoming:
- Write operations with safety controls
- Idempotent ensure methods
- Docker containerization
🤝 Contributing
This project is under active development. See our GitHub Issues for:
- Current development priorities
- Feature requests and roadmap
- Bug reports and discussions
📄 License
MIT License - see LICENSE file for details.
🔗 Related Projects
- Enterprise network automation tools - Production-ready MCP servers
- NetBox - The network documentation and IPAM application
⚠️ Development Notice: This is a development version with write capabilities. Always use proper safety measures and test in non-production environments.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。