# MCP Sandbox Computer VM for AI (pypi · mcp-sandbox-computer-vm-for-ai)

Named Docker and Fly Machine sandbox computers with an interactive MCP App dashboard.

- Trust score: 68/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-19

## Components

- pypi · `mcp-sandbox-computer-vm-for-ai`: 68/100 (this document), [markdown](https://verifymcp.io/servers/flujo-app-mcp-sandbox-computer-vm-for-ai/mcp-sandbox-computer-vm-for-ai.md), [page](https://verifymcp.io/servers/flujo-app-mcp-sandbox-computer-vm-for-ai/mcp-sandbox-computer-vm-for-ai)

## Channel facts

- Registry: `pypi`
- Package: `mcp-sandbox-computer-vm-for-ai`
- Version: `0.2.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-19.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 7 of 66 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (MIT License) isn't a recognized OSI-approved license.
  - Actively maintained (last published 6 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 487 tokens (~60/item across 8 items; 7 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add flujo-app-mcp-sandbox-computer-vm-for-ai -- uvx mcp-sandbox-computer-vm-for-ai
```

### Codex

```bash
codex mcp add flujo-app-mcp-sandbox-computer-vm-for-ai -- uvx mcp-sandbox-computer-vm-for-ai
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "flujo-app-mcp-sandbox-computer-vm-for-ai": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-sandbox-computer-vm-for-ai"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add flujo-app-mcp-sandbox-computer-vm-for-ai --command uvx --arg mcp-sandbox-computer-vm-for-ai
```

### Hermes

```yaml
mcp_servers:
  flujo-app-mcp-sandbox-computer-vm-for-ai:
    command: "uvx"
    args: ["mcp-sandbox-computer-vm-for-ai"]
```

### Other

```json
{
  "mcpServers": {
    "flujo-app-mcp-sandbox-computer-vm-for-ai": {
      "command": "uvx",
      "args": [
        "mcp-sandbox-computer-vm-for-ai"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-14 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-13 (score 53, −15)

- [security regression] Malware scan: pass → unverified

### 2026-08-12 (score 68)

First indexed and scored.

## MCP tools (7)

### `sandbox_exec` (~247 tokens)

Execute a shell command in an isolated Debian Linux sandbox. Commands run in bash. Each call is independent — no state (shell variables, working directory) persists between calls (however filesystem does persist). Use the working_directory parameter or chain commands with && to control execution context. 

To write files or pass data without shell escaping, use the stdin parameter (e.g., command="cat > file.txt" with content in stdin). Commands time out after 120 seconds by default (override with the timeout parameter for long-running operations).

Input parameters:

- `args` (array): List of arguments for direct execution (mutually exclusive with command).
- `command` (string): Shell command string (mutually exclusive with args).
- `computer_id` (string): Stable computer slug. Omit to create and select a readable random ID for this MCP session.
- `stdin` (string): Content to pipe to stdin.
- `temporary` (boolean): Remove the computer when its MCP session shuts down. Set false to keep it provider-side and reconnect by computer_id.
- `timeout` (integer): Timeout in seconds (defaults to server config).
- `working_directory` (string): Working directory for the command (must be absolute).

### `computer_dashboard` (~31 tokens)

Sandbox Computer Dashboard

Open the interactive MCP App dashboard for listing computers, running terminal commands, restarting, factory-resetting, and deleting.

### `computer_list` (~18 tokens)

List all sandbox computers managed by the selected backend.

### `computer_create` (~73 tokens)

Create a temporary or permanent sandbox computer. If computer_id is omitted, a readable random slug is returned.

Input parameters:

- `computer_id` (string): Optional lowercase slug. Omit to generate a readable random ID.
- `temporary` (boolean): Remove on MCP session shutdown when true; persist and allow reattachment by ID when false.

### `computer_restart` (~30 tokens)

Restart a computer without erasing its writable filesystem.

Input parameters:

- `computer_id` (string, required): Computer slug to restart

### `computer_factory_reset` (~40 tokens)

Erase a computer's writable filesystem and recreate it from the base image.

Input parameters:

- `computer_id` (string, required): Computer slug whose writable state will be erased

### `computer_delete` (~33 tokens)

Permanently delete a computer and all of its writable state.

Input parameters:

- `computer_id` (string, required): Computer slug to permanently delete

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/flujo-app-mcp-sandbox-computer-vm-for-ai/mcp-sandbox-computer-vm-for-ai#diagnostics

## Score history

- 2026-08-19: 68
- 2026-08-18: 68
- 2026-08-17: 68
- 2026-08-16: 68
- 2026-08-15: 68
- 2026-08-14: 68
- 2026-08-13: 53
- 2026-08-12: 68

## Links

- PyPI project: https://pypi.org/project/mcp-sandbox-computer-vm-for-ai/
- Socket report: https://socket.dev/pypi/package/mcp-sandbox-computer-vm-for-ai
- Repository: https://github.com/flujo-app/mcp-sandbox-computer-vm-for-ai
- Changelog RSS feed: https://verifymcp.io/servers/flujo-app-mcp-sandbox-computer-vm-for-ai/mcp-sandbox-computer-vm-for-ai.xml
- Changelog JSON feed: https://verifymcp.io/servers/flujo-app-mcp-sandbox-computer-vm-for-ai/mcp-sandbox-computer-vm-for-ai.json
- HTML version of this page: https://verifymcp.io/servers/flujo-app-mcp-sandbox-computer-vm-for-ai/mcp-sandbox-computer-vm-for-ai