← ClaudeAtlas

control-oslisted

Control and inspect the local Linux host through systemd, journald, logind, and D-Bus via the os-control MCP. Use this whenever the user wants to manage or diagnose the machine itself rather than files or GUIs: "restart/stop/start/enable the X service", "is X running / why did it crash", "show me the logs for X / what's in the journal", "what's eating CPU/RAM/disk", "list failed units", "reboot/suspend/power off the box", "notify me on the desktop when Y", "what's on the system D-Bus". Prefer it over raw `kill`/ad-hoc shell for service and power management — it uses the sanctioned interfaces (systemctl/loginctl/journalctl/busctl) and has guards that stop you from cutting off your own access. NOT for editing files, GUI apps (use screen-mcp), or remote hosts.
88plug/os-control-mcp · ★ 0 · AI & Automation · score 60
Install: claude install-skill 88plug/os-control-mcp
# Controlling the OS with os-control-mcp The sanctioned "motor cortex" for the host: act through systemd / logind / journald / D-Bus, not raw PID hacks. **Full tool inventory (22):** - **Sense:** `os_diag`, `os_services`, `os_journal`, `os_resources`, `os_processes`, `os_pressure`, `os_net`, `os_disk`, `os_hardware`, `os_containers`, `os_sensors`, `os_session`, `os_verify` - **Act:** `os_service`, `os_power`, `os_dbus`, `os_time`, `os_hostname`, `os_locale`, `os_notify` - **Confirm / meta:** `os_wait`, `os_reload` ## The loop: sense → act → confirm 1. **Sense first.** `os_diag` (health, privilege, backends) → observe with `os_services` / `os_journal` / `os_resources` / `os_processes` / `os_pressure` / `os_net` / `os_disk` / `os_hardware` / `os_containers` / `os_sensors` / `os_session`. Understand state before changing it. 2. **Act through the sanctioned tool.** `os_service` (start/stop/restart/enable/…), `os_power` (suspend/reboot/poweroff), `os_dbus` / `os_time` / `os_hostname` / `os_locale` / `os_notify`. 3. **Confirm.** `os_wait` and/or re-run `os_services unit=…` / `os_journal unit=…` — don't assume the action took. ## The two guards (and how to pass them) - **Self-preservation guard.** A *severing* action (stop/restart/disable/mask/kill) on a unit the agent depends on — `dbus`, `systemd-logind`, `sshd`, `NetworkManager`/networkd, `tailscaled`, the `user@…` session, `goosed`, etc. — is **REFUSED**. This stops you cutting off your own bus / login / network / remote a