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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.