automation-health-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_jobsA | List scheduled jobs (launchd on macOS, systemd on Linux) with exit status. Args: prefix: only return jobs whose label starts with this string, e.g. "com.mycompany." to skip the operating system's own jobs. |
| find_failing_jobsA | Return only the scheduled jobs whose last run exited with an error. |
| check_log_freshnessA | Report logs that have not been written to recently. A daily job whose log is 26 hours old has not run. This is the cheapest liveness check available and it requires no instrumentation. |
| check_recent_errorsA | Scan the tail of recently-written logs for error signatures. Only recent files and only their last lines, so that failures fixed last week do not keep reappearing in the report. |
| check_endpointA | Check an integration by its payload, not its status code. Set |
| find_stale_placeholdersA | Find functions marked TODO that still return a hardcoded value. Catches the reporting function that reads its input file, ignores it, and returns the constant it was seeded with during development. |
| auditA | Run every check and return one prioritised report. This is the tool to call first. It answers: what on this machine is broken right now and nobody has been told? |
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 7 tools
Mostly distinct purposes: list_jobs lists, find_failing_jobs filters, check_log_freshness and check_recent_errors both target logs but with different focus (staleness vs errors), and audit is an umbrella. check_log_freshness vs check_recent_errors could cause some confusion since both deal with recent log analysis, but their descriptions are clear enough.
Consistent verb_noun pattern: list_jobs, find_failing_jobs, check_log_freshness, check_recent_errors, check_endpoint, find_stale_placeholders, audit. The verbs vary somewhat (list/find/check/audit) but all follow the same shape and audit as a single verb is a reasonable deviation as the umbrella command.
Seven tools is a well-scoped set for a system health/automation monitoring server. Each tool covers a distinct monitoring concern: jobs, logs, endpoints, placeholders, and a meta-tool that aggregates. No bloat, no obvious filler.
The surface covers the main health-monitoring concerns: job listing, failure detection, log freshness, log error scanning, endpoint verification, and placeholder detection, plus an aggregate audit. Minor gaps exist (e.g., no tool to trigger or retry a job, no alerting mechanism exposed), but the core monitoring workflow is complete.