Linuxfabrik MCP Server for Icinga
Enables AI clients like Claude to triage, investigate, and operate Icinga installations through natural language, integrating with Icinga's REST APIs and providing deep awareness of monitoring plugins and historical performance data.
README
<h1 align="center"> Linuxfabrik MCP Server for Icinga </h1> <p align="center"> Model Context Protocol (MCP) server for Icinga. Lets AI clients such as Claude triage, investigate and operate Icinga installations through the Icinga 2 Core, Icinga Web and Icinga Director REST APIs, with deep awareness of the Linuxfabrik monitoring-plugins catalog and historical perfdata from a time series database. <span>•</span> <b>made by <a href="https://linuxfabrik.ch/">Linuxfabrik</a></b> </p> <div align="center">
</div>
<br />
MCP Server for Icinga
mcp-server-icinga is a Model Context Protocol (MCP) server that lets AI clients such as Claude work with Icinga installations through natural language. It targets Linux System Engineers who run Icinga in production and want a chat-driven interface for daily triage, incident investigation and routine operations on top of the existing Icinga REST APIs.
This project was developed with the assistance of Claude Code by Anthropic.
Scope
The server bridges three Icinga surfaces and the Linuxfabrik monitoring stack:
- Icinga 2 Core REST API (port 5665): live host and service objects, on-demand checks, acknowledgements, downtimes.
- Icinga Web 2 / Icinga DB Web module: richer state projections, history, comments, notifications, with the limitations of the Icinga Web surface.
- Icinga Director API: object browsing, service template introspection, command catalog.
- Linuxfabrik monitoring-plugins catalog: implementation, inputs, outputs, states and perfdata of every check plugin, so the server can explain why a service is alerting, not just that it is.
- Time series database (default: InfluxDB, modular): historical perfdata for trending, flapping analysis and root-cause investigation.
Each backend lives in its own module so that operators can wire up only what they actually run. The server transparently flags information that the underlying API does not expose, instead of guessing.
Status
Early development. Architecture, configuration and tool surface are unstable and will change.
Requirements
- Python 3.14 or newer.
- Reachable Icinga installation (one or more of: Icinga 2 Core API, Icinga Web 2 with the Icinga DB Web module, Icinga Director).
- Optional: a time series database backend for historical perfdata. Default integration is InfluxDB; the TSDB layer is modular so other backends can be plugged in.
Installation
Installation instructions will be documented once the first release is cut.
Configuration
Configuration documentation will follow as soon as the configuration surface stabilises.
Related Projects
- Linuxfabrik monitoring-plugins: the check plugin catalog this server understands.
- Linuxfabrik lib: shared Python helpers.
- Icinga/icinga-mcp: upstream proof-of-concept MCP server by the Icinga team. Different scope, different architecture.
License
Released into the public domain under the Unlicense.
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。