opsgate
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": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| compose_psC | List services of a Docker Compose project in a directory. |
| dir_listB | List a directory under one of the configured allowed paths. |
| disk_usageA | Show mounted filesystem usage (df -h) for a host. |
| docker_inspectA | Inspect a container's health, restart count, image and mounts. |
| docker_logsC | Read the recent logs of a Docker container. |
| docker_psB | List Docker containers with status, image and ports. |
| docker_restartC | Restart a Docker container. |
| docker_startC | Start a stopped Docker container. |
| docker_statsB | Show a one-shot snapshot of container CPU and memory usage. |
| docker_stopC | Stop a running Docker container. |
| file_grepB | Search a file for a fixed string. Useful for finding an error in a large log. |
| file_readA | Read a file under one of the configured allowed paths (see files.allow_paths). |
| journal_errorsA | Show recent error-and-worse journal entries across the system — a fast triage starting point. |
| journal_tailB | Read recent systemd journal entries, optionally filtered by unit, time and priority. |
| listening_portsB | List listening TCP/UDP sockets and the processes owning them. |
| nginx_reloadA | Reload nginx. Validates the configuration first and refuses to reload a broken config. |
| nginx_testA | Validate the nginx configuration (nginx -t) without applying it. |
| process_topB | List the top processes on a host by CPU or memory usage. |
| service_listB | List systemd services on a host, optionally filtered to running or failed units. |
| service_reloadA | Reload a systemd service's configuration without restarting it. |
| service_restartC | Restart a systemd service. |
| service_startB | Start a stopped systemd service. |
| service_statusB | Show the status of one systemd service, including recent log lines. |
| service_stopC | Stop a running systemd service. |
| system_infoB | Show kernel, uptime, load average and memory usage for a host. |
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 25 tools
Most tools target a clearly distinct resource+action (docker_start/stop/restart, service_start/stop/restart/reload, nginx_test/reload). A couple of pairs overlap, notably journal_errors vs journal_tail (the former is just a filtered convenience view) and service_status's embedded log lines vs journal_tail, but descriptions mostly disambiguate.
Strong resource_action pattern throughout (docker_*, service_*, file_*, journal_*, nginx_*), so an agent can predict names. Minor deviations: compose_ps uses 'ps' like docker_ps while systemd uses service_list, and a few tools (disk_usage, listening_ports, system_info) are descriptive rather than verb-form.
25 tools is at the heavy end but spread across seven genuine domains (Docker, Compose, systemd, nginx, files, journal, network/system), so each tool earns its place. It sits just above the comfortable 3-15 band but the breadth justifies it.
Covers the core lifecycle for containers and services (list/status/start/stop/restart/reload/inspect/logs/stats) plus diagnostics and config validation for nginx. Gaps are minor and largely intentional (no file write, no docker exec, no compose up/down), which an agent can work around via service/file tools.