
vibeMK
io.github.chexmav0.6.4Updated Oct 3, 2026
Query and configure CheckMK monitoring: hosts, services, rules, downtimes, metrics
Overview
Lets an assistant read and change CheckMK monitoring through natural language: hosts, services, rules, downtimes, metrics and users.
- What it does
- vibeMK connects an assistant to a CheckMK monitoring site. It reads live host and service states, performance metrics and current problems, and it can schedule downtimes, acknowledge or remove acknowledgements, and create folders, rules, time periods, host groups, tags, user accounts and contact groups. It supports CheckMK 2.3.x through 2.5.x, with Raw, Enterprise and Cloud editions.
- When to use it
- Use it when you want to inspect or administer a CheckMK environment conversationally, for example to check what is currently down, compare metrics between hosts, schedule maintenance windows, or review and consolidate rulesets. A read-only mode is available if you only want analysis.
- Requirements
- Runs locally as a Python package (pipx, uv or pip) started by the MCP client over stdio. Requires a CheckMK server URL, site name and automation user, plus the automation secret in CHECKMK_PASSWORD; optional CHECKMK_VERIFY_SSL, NEVER_ACTIVATE_CHANGES and VIBEMK_READ_ONLY. The automation user needs administrator permissions for changes, or a read-only role for analysis. An optional HTTP mode needs a bearer token.
Installation
In SourceWeft
- Open vibeMK in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
vibeMK 🚀
CheckMK Monitoring via LLM - Professional MCP Server
[Python 3.10+] [CheckMK 2.3+] [License: GPL v3] [MCP Compatible] [MCP SDK] [Code style: black] [Typed]
🎯 Overview
vibeMK enables complete management of your CheckMK monitoring environment directly through LLM interfaces using natural language. This project is in the alpha stage and under development. I accept no liability for any damage resulting from the use of this software.
vibeMK - Current Features
Live Monitoring ✅
- Host Status: Real-time host state (UP/DOWN/UNREACHABLE) with hard state detection
- Service Status: Live service monitoring (OK/WARNING/CRITICAL/UNKNOWN)
- Performance Metrics: Retrieve metrics data with automatic discovery
- Current Problems: Auto-detect all active monitoring issues
Downtime Management ✅
- Schedule Downtimes: Create host/service downtimes with flexible duration parsing ("2h", "1h30m")
- List & Filter: View all downtimes or filter for active ones only
Problem Management ✅
- Acknowledge Problems: Set acknowledgements for host/service issues (sticky/persistent options)
- List Acknowledgements: View all current problem acknowledgements
- Remove Acknowledgements: Delete by pattern or individual removal
Configuration Management ✅
- Folders: Create/delete monitoring folder structures
- Rules: Create rules for 2000+ CheckMK ruleset types with proper format handling
- Time Periods: Create custom notification schedules (business hours, 24/7, etc.)
- Host Groups: Organize hosts into logical groups
User & Security ✅
- User Accounts: Create/manage user accounts with role assignment
- Password Management: Set passwords with policy enforcement
- Contact Groups: Manage notification groups
- Host/Service Tags: Comprehensive tagging system
🚀 Quick Start
Complete Installation Guide: See INSTALL.md for detailed step-by-step instructions.
Upgrading from 0.3.x or older: git pull is not enough, see Upgrading.
More Examples: See examples/llm_configs/ and INSTALL.md
Visual Examples: See examples/Screenshots/ for example prompts and usage patterns
🔌 Running it
Locally (default). The LLM client starts vibeMK itself over stdio. Nothing to host, nothing to secure -- the client already owns the process.
Centrally. One instance can serve many clients over Streamable HTTP, so they need neither Python nor vibeMK installed:
Clients connect to http://<host>:8765/mcp and send Authorization: Bearer <token>.
The token is mandatory, and vibeMK binds to localhost unless told otherwise:
the CheckMK account lives on the server, so whoever reaches the port inherits
it. See INSTALL.md for what that means before you expose it.
💡 Practical Prompt Examples
Advanced Usage: See examples/ExamplePrompts.md for complex scenarios and tips
📚 Checkmk version compatibility
Checkmk Edition Support
- Raw Edition: Fully supported, including the BI and Event Console endpoints
- Enterprise Edition: Adds the Agent Bakery and custom graphs
- Cloud Edition: All Enterprise features
Edition availability follows the operationId of each endpoint in the Checkmk
OpenAPI document: cmk.gui.cee.* is Enterprise-only, everything else is served
by every edition including Raw.
Security considerations
- To let a model look without touching, start vibeMK read-only:
--read-onlyorVIBEMK_READ_ONLY=1. Only the tools that read are offered, and a call to any other is refused before it reaches CheckMK - Be aware of the potential security risks when you unleash AI on your checkmk
- Use at your own risk
- I accept no responsibility for actions performed by an AI
📄 License
This project is licensed under the GNU General Public License v3.0.
Happy Monitoring with CheckMK and LLMs! 🎉
Source: README.md at commit e1cc869
Tools
0Version history
1- v0.6.4LatestOct 3, 2026

