mcp-nagios-crunchtools
A secure MCP server for Nagios Core that lets you query monitoring status, inspect alert history, and act on problems.
Check individual status — query a single host's or a specific service's current state.
See what's broken now — list all hosts/services in non-OK state with state duration, attempt count, acknowledgement flag and plugin output.
Verify the monitoring system itself — detect a wedged daemon, stale status data (configurable
max_staleness_seconds), or globally disabled notifications/checks; raises on connection failure so a dead Nagios can't look healthy.Acknowledge problems — on a host or service, with sticky (default) and notify (default) options plus a comment.
Add comments — persistent notes on a host or service.
Force re-checks — schedule an immediate check of a host or service.
Review notification history — past notifications over 1–744 hours, optionally filtered to one host.
Analyze alert history — per-host/service rollup of state changes, including warnings, soft states and problems that recovered without paging, which surfaces flapping.
Note: the exposed schema has 10 tools; the downtime tools described in the README (schedule, list, cancel, history) are not present in this server's tool list.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-nagios-crunchtools show all current host and service problems"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-nagios-crunchtools
Secure MCP server for Nagios Core monitoring. Query host and service status, acknowledge problems, add comments, schedule forced checks, and read notification history.
Installation
uvx mcp-nagios-crunchtoolsRelated MCP server: thruk-mcp
Configuration
Variable | Required | Description |
| Yes | Base URL (e.g., |
| Yes | HTTP Basic Auth username |
| Yes | HTTP Basic Auth password |
| No | Author recorded on acknowledgements and comments. Defaults to |
| No | Path under |
| No | Read-only path to |
| Effectively yes | The container's local timezone. Must match the Nagios server's own timezone. |
Why TZ matters
schedule_check submits a start_time to cmd.cgi, which parses it as naive
wall-clock time in the Nagios server's local timezone — there is no offset field
to send. The value is therefore built with time.localtime(), so this container
must run in the same timezone as the Nagios server.
When it does not, forced checks are silently scheduled into the future by the
offset between the two — four hours against an EDT server — and "check now"
appears to do nothing at all. No error is raised. This was a real defect, fixed
in 0.1.2 by switching from gmtime() to localtime(); the timezone assumption
it introduced is why TZ belongs in this table rather than being left implicit.
Tools
Tool | Description |
| Query a single host's status |
| Query a single service's status |
| All hosts/services not in OK state, with duration, attempt, acknowledgement and plugin output |
| Health check on the monitoring path itself (wedged daemon, disabled notifications, stale status) -- not the same as no current problems |
| Acknowledge a host or service problem |
| Add a comment to a host or service |
| Force an immediate re-check |
| Fixed downtime from now (5–480 min) on a host and its services, or one service, before planned work |
| Downtime in effect or pending |
| End this server's own downtime when the work is done |
| Past and current downtime windows with author and comment, from |
| Recent notifications |
| State changes rolled up per host/service, including warnings and problems that recovered by themselves; problems during scheduled downtime are totalled separately |
License
AGPL-3.0-or-later
Available Tools
13 toolsnagios_acknowledge_toolNagios Acknowledge ToolC
Acknowledge a host or service problem in Nagios.
Inputs: comment (required), host_name (required), notify, sticky, +1 more. Returns: result
nagios_add_comment_toolNagios Add Comment ToolB
Add a persistent comment to a host or service in Nagios.
Inputs: comment (required), host_name (required), service_description. Returns: result
nagios_alert_history_toolNagios Alert History ToolARead-only
Roll up Nagios state changes per host and service over a period.
Unlike notification history, this includes warnings, soft states and problems that recovered without paging anyone, so it is where flapping shows.
Inputs: hours, host_name. Returns: result
nagios_cancel_downtime_toolNagios Cancel Downtime ToolA
End downtime this server scheduled, once the planned work is done.
Only downtime recorded under this server's own author is cancelled.
Inputs: host_name (required), service_description. Returns: result
nagios_current_problems_toolNagios Current Problems ToolARead-only
List all hosts and services currently in a non-OK state.
Inputs: no named parameters. Returns: result
nagios_downtime_history_toolNagios Downtime History ToolBRead-only
List past and current downtime windows, read from nagios.log.
Inputs: hours, host_name. Returns: result
nagios_host_status_toolNagios Host Status ToolBRead-only
Get the current status of a Nagios host.
Inputs: host_name (required). Returns: result
nagios_list_downtimes_toolNagios List Downtimes ToolARead-only
List scheduled downtime that is in effect or still to come.
Inputs: host_name. Returns: result
nagios_notification_history_toolNagios Notification History ToolBRead-only
Retrieve recent notification history from Nagios.
Inputs: hours, host_name. Returns: result
nagios_program_status_toolNagios Program Status ToolARead-only
Check whether the Nagios daemon itself is alive and actually working.
Use this to verify the monitoring system, NOT to find outages. It is the right tool for a watchdog asking "is Nagios still able to tell me about problems?" -- nagios_current_problems_tool answers a different question and returns "no problems" both when all is well and when Nagios has silently stopped working.
Detects a wedged daemon (CGI still returns 200 but status data is stale), globally disabled notifications (monitoring everything, alerting nobody), and disabled check execution. Raises on connection failure, so a dead Nagios can never be read as healthy.
Inputs: max_staleness_seconds. Returns: result
nagios_schedule_check_toolNagios Schedule Check ToolC
Schedule a forced immediate re-check of a host or service.
Inputs: host_name (required), service_description. Returns: result
nagios_schedule_downtime_toolNagios Schedule Downtime ToolA
Schedule fixed downtime starting now, before planned work makes checks fail.
Notifications stop for the window, and alert history counts problems inside it as planned work rather than noise. Cancel it with nagios_cancel_downtime_tool when the work is done.
Inputs: comment (required), minutes (required), host_name (required), service_description. Returns: result
nagios_service_status_toolNagios Service Status ToolBRead-only
Get the current status of a specific service on a host.
Inputs: host_name (required), service_description (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Each tool targets a distinct action or data view, and descriptions actively disambiguate tricky pairs (program_status vs current_problems, alert_history vs notification_history, downtime_history vs list_downtimes). The only mild overlap is between downtime_history ('past and current') and list_downtimes ('in effect or still to come'), which could still confuse an agent about which covers active windows.
All 13 tools follow the same nagios_<verb/noun>_tool pattern (nagios_acknowledge_tool, nagios_schedule_downtime_tool, etc.), with no camelCase or style mixing. Predictable and easy to scan.
13 tools is well within the ideal range and each maps to a concrete monitoring operation (status queries, acknowledgements, comments, downtime lifecycle, history, self-health). No filler or redundant tools are apparent.
Core read lifecycle (host/service status, current problems, program status) and downtime lifecycle (schedule/cancel/list/history) plus acknowledgement and comments are covered. Minor gaps exist: no unacknowledge/remove-comment, no enable/disable notifications, and no host/service inventory enumeration, but these are workaroundable.
Maintenance
Related MCP Connectors
Read NodePing checks, uptime, results and events; mute checks, manage maintenance and schedules.
Cron, uptime, DNS, SSL and domain monitoring. Manage checks, dashboards and alerts; read incidents.
Read Status.io components, incidents, maintenance; post incidents, schedule maintenance, set status.
Pingstack monitors cron jobs and scheduled tasks with heartbeat checks, and checks websites, TCP ports, DNS records, SSL certificates and domain expiry. This MCP server lets your agent create, update, pause and delete checks, build dashboards and publish them as status pages, manage notification groups, and read incidents with their causes, uptime, run history and latency. Pause, delete and unpublish stay off until you turn them on. Browser sign-in, no API key needed.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables 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.5-
- AlicenseCqualityCmaintenanceEnables natural language interaction with Thruk monitoring systems, allowing users to query hosts/services, schedule downtimes, acknowledge problems, and more via MCP-compatible clients.652MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for Nagios Core that enables querying host and service status, alerts, configuration, and other monitoring data through CGI binaries.5Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables interaction with N-able RMM (N-sight) API to manage clients, sites, devices, and retrieve monitoring data such as checks, patches, and performance history.Apache 2.0