# run_script

Upload a temporary bash script to the Ubuntu server and execute it.

Agent View of the PolicyLayer registry record for `run_script`. HTML page: https://policylayer.com/tools/mcp-control-plane/run-script

## Facts

- Tool: `run_script`
- Server: Mcp Control Plane (`albertik322-sudo/mcp-control-plane`) — https://policylayer.com/tools/mcp-control-plane.md
- Homepage: https://github.com/albertik322-sudo/mcp-control-plane
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run_script",
    "arguments": {}
  }
}
```

## Why run_script is rated High

This tool allows execution of arbitrary shell commands on a remote Ubuntu server with no inherent restrictions on what those commands can do. An AI agent given this capability could read sensitive files, modify system state, install malware, exfiltrate data, or cause denial of service.

From the tool's own definition: "Tool description states it 'Upload a temporary bash script to the Ubuntu server and execute it.' The direct execution of arbitrary bash scripts on a server is a classic Execute action with potentially unlimited blast radius."

## Use case

AI agents invoke run_script to trigger actions in Mcp Control Plane. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Mcp Control Plane:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_script": {
      "limits": [
        {
          "counter": "run_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Mcp Control Plane (285)

- `request_durable_task_cancel` — Destructive — https://policylayer.com/tools/mcp-control-plane/request-durable-task-cancel.md
- `steam_rom_manager_cli` — Destructive — https://policylayer.com/tools/mcp-control-plane/steam-rom-manager-cli.md
- `steam_rom_manager_nuke` — Destructive — https://policylayer.com/tools/mcp-control-plane/steam-rom-manager-nuke.md
- `steam_rom_manager_remove` — Destructive — https://policylayer.com/tools/mcp-control-plane/steam-rom-manager-remove.md
- `activate_window` — Execute — https://policylayer.com/tools/mcp-control-plane/activate-window.md
- `admin_run` — Execute — https://policylayer.com/tools/mcp-control-plane/admin-run.md
- `api_sentence` — Execute — https://policylayer.com/tools/mcp-control-plane/api-sentence.md
- `apply_unified_patch_remote` — Execute — https://policylayer.com/tools/mcp-control-plane/apply-unified-patch-remote.md
- `apt_maintenance` — Execute — https://policylayer.com/tools/mcp-control-plane/apt-maintenance.md
- `call_service` — Execute — https://policylayer.com/tools/mcp-control-plane/call-service.md
- `click` — Execute — https://policylayer.com/tools/mcp-control-plane/click.md
- `click_at` — Execute — https://policylayer.com/tools/mcp-control-plane/click-at.md
- `click_in_window` — Execute — https://policylayer.com/tools/mcp-control-plane/click-in-window.md
- `comfy_generate_from_asset` — Execute — https://policylayer.com/tools/mcp-control-plane/comfy-generate-from-asset.md
- `comfy_interrupt` — Execute — https://policylayer.com/tools/mcp-control-plane/comfy-interrupt.md
- `comfy_restart` — Execute — https://policylayer.com/tools/mcp-control-plane/comfy-restart.md
- `deck_exec` — Execute — https://policylayer.com/tools/mcp-control-plane/deck-exec.md
- `deck_probe` — Execute — https://policylayer.com/tools/mcp-control-plane/deck-probe.md
- `dns_test` — Execute — https://policylayer.com/tools/mcp-control-plane/dns-test.md
- `docker_compose` — Execute — https://policylayer.com/tools/mcp-control-plane/docker-compose.md
- `docker_container_action` — Execute — https://policylayer.com/tools/mcp-control-plane/docker-container-action.md
- `docker_exec` — Execute — https://policylayer.com/tools/mcp-control-plane/docker-exec.md
- `double_click` — Execute — https://policylayer.com/tools/mcp-control-plane/double-click.md
- `drag_to` — Execute — https://policylayer.com/tools/mcp-control-plane/drag-to.md
- `focus_window_win32` — Execute — https://policylayer.com/tools/mcp-control-plane/focus-window-win32.md
- `hold_key` — Execute — https://policylayer.com/tools/mcp-control-plane/hold-key.md
- `hotkey` — Execute — https://policylayer.com/tools/mcp-control-plane/hotkey.md
- `install_flatpak_emulators` — Execute — https://policylayer.com/tools/mcp-control-plane/install-flatpak-emulators.md
- `key_down` — Execute — https://policylayer.com/tools/mcp-control-plane/key-down.md
- `key_up` — Execute — https://policylayer.com/tools/mcp-control-plane/key-up.md
- …and 255 more: https://policylayer.com/tools/mcp-control-plane.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=mcp-control-plane · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/mcp-control-plane