mcp-nagios-crunchtools
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NAGIOS_URL | Yes | Base URL (e.g., https://nagios.crunchtools.com) | |
| NAGIOS_PASS | Yes | HTTP Basic Auth password | |
| NAGIOS_USER | Yes | HTTP Basic Auth username |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| nagios_host_status_toolB | Get the current status of a Nagios host. |
| nagios_service_status_toolB | Get the current status of a specific service on a host. |
| nagios_current_problems_toolA | List all hosts and services currently in a non-OK state. Returns: One line per problem with its state, how long it has been in that state, attempt count, acknowledgement and plugin output, or confirmation that everything is OK. |
| nagios_program_status_toolA | 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. |
| nagios_acknowledge_toolC | Acknowledge a host or service problem in Nagios. |
| nagios_add_comment_toolB | Add a persistent comment to a host or service in Nagios. |
| nagios_schedule_check_toolC | Schedule a forced immediate re-check of a host or service. |
| nagios_notification_history_toolB | Retrieve recent notification history from Nagios. |
| nagios_alert_history_toolA | 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool targets a distinct Nagios concept or action: current problems vs. daemon health (explicitly contrasted), host status vs. service status, notification history vs. alert history (differentiated by scope). The descriptions actively call out the tricky overlaps, leaving little room for misselection.
Every tool follows the same nagios_<concept>_tool snake_case pattern with a uniform prefix and suffix. Action tools (acknowledge, add_comment, schedule_check) and query tools are all rendered in the identical convention.
Nine tools is well-scoped for a Nagios monitoring/inspection surface, with each tool earning its place covering distinct read and light-action operations. No redundancy or filler.
Core monitoring workflows are covered: problem listing, daemon health, host/service status, acknowledgement, comments, forced checks, and two history views. Minor gaps exist around scheduled downtime and enable/disable notifications, but agents can work around these.