safe-ssh-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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_disk_freeC | Collects disk usage (df -h) from a remote Linux host via SSH. |
| get_inode_usageC | Collects inode usage (df -i) from a remote Linux host via SSH. |
| get_disk_usageA | Collects disk usage for a specific abs path from a remote Linux host via SSH. Returns the top 20 largest files/folders in the specified directory. |
| get_list_of_filesB | Collects list of files for a specific abs path from a remote Linux host via SSH. Returns with -lah option |
| get_list_of_files_with_filterA | Collects list of files for a specific abs path with filter (grep) applied from a remote Linux host via SSH. -lah option is applied. |
| get_is_installedC | Checks whether a binary/command is installed and callable on a remote Linux host via SSH. |
| get_dmesgC | Collects dmesg log from a remote Linux host via SSH |
| get_uptimeA | Collects uptime from a remote Linux host via SSH |
| get_current_datetimeB | Collects current datetime from a remote Linux host via SSH |
| get_distroname_versionC | Collects distr details from os-release from a remote Linux host via SSH |
| get_systemd_list_allC | Lists all systemd units. USE THIS TOOL to check for running, stopped, or FAILED daemon/service/unit. |
| get_systemd_list_failedA | Lists failed systemd units. USE THIS TOOL to check for FAILED daemons/services/units. |
| get_systemd_list_timersC | Lists all systemd timers. USE THIS TOOL to check for timers. |
| get_systemd_statusC | Gets the detailed status, logs, and error messages for a SPECIFIC systemd daemon/service/unit. |
| get_ps_aux_top_cpu_consumersC | Lists top 10 cpu consumers, CPU desc |
| get_ps_aux_top_mem_consumersC | Lists top 10 mem consumers, MEM desc |
| get_free_memoryC | Returns free memory, swap (total/free), page cache, HugePages and so on |
| get_memory_pressureD | Returns memory pressure if supported |
| get_topC | Collects top's snapshot from a remote Linux host via SSH |
| get_lsblkC | Collects lsblk output from a remote Linux host via SSH |
| get_docker_ps_allA | Collects docker ps --all output from a remote Linux host via SSH |
| get_crontab_tasksC | Collects crontab -l (crontab list) output from a remote Linux host via SSH |
| get_listening_socketsB | Collects ss -tulpn output (open ports and sockets) from a remote Linux host via SSH |
| get_service_logs_from_journalctlC | Gets recent journald logs for a specific systemd service. |
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 24 tools
Most tools target distinct system aspects, but slight overlap exists between get_disk_free/get_disk_usage and get_free_memory/get_memory_pressure. The two file listing tools are differentiated by filter usage, which is clear.
All tool names follow a strict 'get_' prefix followed by a descriptive noun phrase (e.g., get_crontab_tasks, get_current_datetime). The pattern is uniform and predictable.
24 tools is on the higher side but reasonable for a comprehensive system diagnostic server. Each tool covers a specific diagnostic need, though a few could be merged (e.g., get_disk_free and get_disk_usage) without loss of clarity.
The set covers many essential diagnostics: disk, memory, CPU, processes, systemd, docker, and files. However, it lacks network diagnostics beyond listening sockets, IO stats, and user-related queries, leaving some gaps for a full system assessment.