agentleFS
sandraschisandraschi/virtualization-mcp/llms-full.txt

virtualization-mcp

llms.txt17 starsChanged 34 days agoMITView on GitHub

FastMCP 3.2 server with modular plugin architecture. VirtualBox operations via VBoxManage CLI (direct) and vboxapi/pyvbox (compat layer). Hyper-V via PowerShell cmdlets. Docker sandbox via Docker SDK. Portmanteau mode consolidates 60+ individual operations into 8 portmanteau tools with 33+ operations.

The file

We split this llms-full.txt into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All tools return {"success": bool, "action": str, "data": {...}} or {"success": false, "error": str}.

    line 116

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms-full.txt
# virtualization-mcp — Full Reference

## Architecture

FastMCP 3.2 server with modular plugin architecture. VirtualBox operations via VBoxManage CLI (direct) and vboxapi/pyvbox (compat layer). Hyper-V via PowerShell cmdlets. Docker sandbox via Docker SDK. Portmanteau mode consolidates 60+ individual operations into 8 portmanteau tools with 33+ operations.

### Supported Hypervisors

| Platform | Mode | Interface |
|----------|------|-----------|
| VirtualBox 7+ | Primary | VBoxManage CLI + pyvbox compat |
| Hyper-V | Windows only | PowerShell (Get-VM, Start-VM, etc.) |
| Windows Sandbox | Windows only | Native .wsb configuration |
| Docker | Container | Docker SDK for Python |

## Tools — Full Reference

### vm_management

| Operation | Description |
|-----------|-------------|
| `list` | List all VMs (status, RAM, CPUs, OS) |
| `create` | Create VM (name, OS type, RAM, disk) |
| `start` | Start VM (headless or GUI) |
| `stop` | Stop VM (acpi/shutdown/poweroff) |
| `delete` | Delete VM and associated files |
| `clone` | Clone VM with new name and MAC policy |
| `reset` | Reset VM (hard reset) |
| `pause` | Pause VM (save state) |
| `resume` | Resume paused VM |
| `info` | Detailed VM config and runtime status |

### network_management

| Operation | Description |
|-----------|-------------|
| `list_networks` | List host-only networks (name, CIDR, DHCP) |
| `create_network` | Create host-only network with DHCP |
| `remove_network` | Remove host-only network |
| `list_adapters` | List VM network adapters |
| `configure_adapter` | Attach adapter (NAT/bridged/host-only/internal) |

### snapshot_management

| Operation | Description |
|-----------|-------------|
| `list` | List snapshots for a VM (name, UUID, timestamp, description) |
| `create` | Create snapshot with optional description |
| `restore` | Restore VM to snapshot state |
| `delete` | Delete snapshot |

### storage_management

| Operation | Description |
|-----------|-------------|
| `list_controllers` | List storage controllers on a VM |
| `create_controller` | Create IDE/SATA/SCSI/SAS/USB/PCIe controller |
| `remove_controller` | Remove storage controller |
| `list_disks` | List virtual disks |
| `create_disk` | Create new VDI/VMDK/VHD disk |
| `attach_disk` | Attach disk to VM controller port |

### system_management

| Operation | Description |
|-----------|-------------|
| `host_info` | Host system information (OS, CPU, RAM) |
| `vbox_version` | VirtualBox version and extension pack status |
| `ostypes` | List available OS type identifiers |
| `metrics` | VM performance metrics (CPU, RAM, disk, network) |
| `screenshot` | Take VM screenshot (PNG) |

### sandbox_management (Docker)

| Operation | Description |
|-----------|-------------|
| `execute_code` | Run code in ephemeral container (python/javascript/bash) |
| `execute_file` | Run host script file in ephemeral container |
| `session_create` | Create stateful container session |
| `session_run` | Execute command in session container |
| `session_write_file` | Write file into session container |
| `session_read_file` | Read file from session container |
| `session_list` | List active sessions |
| `session_destroy` | Remove session container |

### hyperv_management

| Operation | Description |
|-----------|-------------|
| `list` | List Hyper-V VMs |
| `get` | Detailed VM info |
| `start` | Start VM |
| `stop` | Stop VM (force/wait options) |

### agentic_tools (LLM sampling)

- `suggest_config` — LLM recommends VM settings for use case (CI, malware sandbox, dev env)
- `sandbox_workflow` — Step-by-step plan for spin-up → work → snapshot → tear-down
- `workflow` — Autonomous multi-step VM orchestration

### virtualization_shutdown

- Graceful self-termination for agents (reason param, exits after responding).

## REST Endpoints (webapp backend, port 10701)

- `GET /api/v1/health`, `GET /health` — liveness probes
- `GET /api/v1/diagnostics` — tool list, system info, errors (CUA-NSIS smoke)
- `POST /api/shutdown` — orderly exit (responds 200, exits after 500 ms)
- `GET /api/v1/dashboard`, `/api/v1/status`, `/api/v1/skills`, `/api/v1/chat`,
  `/api/llm/*` (providers, models, chat proxy), `/api/v1/sandbox/*`,
  `/api/v1/fleet/naked-test*`, `/api/v1/vms*` (incl. VRDE/VNC), `/mcp/tools`

## Error Handling

All tools return `{"success": bool, "action": str, "data": {...}}` or `{"success": false, "error": str}`. VBoxManage errors propagated directly. Async operations use thread pool — never block event loop.

## Cross-repo Integration

- **openclaw-molt-mcp** — Sandbox provision for OpenClaw isolation
- **meta-mcp** — Fleet webapp launch/stop via port detection

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.