MCP Sandbox Computer VM for AI MCP Server

by flujo-app Your server? Claim it

local only

MCP Sandbox Computer VM for AI runs on your own machine — the client starts it, so there is no endpoint to ping. 126 installs a week from pypi. Last commit 7 Sep 2026.

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

Installs per day peak 34 · avg 18 · -19% w/w

a month agotoday

126

Installs / week

pypi · mcp-sandbox-computer-vm-for-ai

Stars

0 open issues

7 Sep 2026

Last commit

from GitHub

MIT

License

Python

What the code does

We read the source, 2 d ago · rules ccca72095570

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Executes code built at runtime src/kilntainers/backends/base.py:132, src/kilntainers/backends/e2b.py:410, src/kilntainers/backends/modal.py:486 и ещё 12

    async def exec(self, request: ExecRequest) -> ExecResult:

Runs an external command [пакет] src/kilntainers/backends/test_docker_integration.py:47, [пакет] src/kilntainers/test_cli_integration.py:22, [пакет] src/kilntainers/test_lifecycle_integration.py:87 и ещё 1

        result = subprocess.run([engine, "info"], capture_output=True, text=True)

Asks for container control access compose.yaml:17

      - /var/run/docker.sock:/var/run/docker.sock

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp-sandbox-computer-vm-for-ai -- uvx mcp-sandbox-computer-vm-for-ai

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

[mcp_servers.mcp-sandbox-computer-vm-for-ai]
command = "uvx"
args = ["mcp-sandbox-computer-vm-for-ai"]

.cursor/mcp.json

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

.vscode/mcp.json

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

Alternatives to MCP Sandbox Computer VM for AI

same job, measured the same way

MCP Virtual Computer

by flujo-app

A persistent Docker or Fly computer with a Three.js interface and optional live Xfce desktop.

246 installs/wk local only

Fly Io

by pulsemcp

MCP server for managing Fly.io machines, apps, logs, and Docker images.

37 installs/wk local only

Open Computer Use

by yambr

Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents

local only

Interactive Terminal

by amol21p

MCP server for real interactive terminal sessions — REPLs, SSH, databases, Docker

81 installs/wk local only

Runeward

by runewardd

Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.

local only

HomeLab Monitor

by sikamikanikobg

Self-hosted homelab dashboard with a built-in read-only MCP server (hosts, Docker, GPU, services).

local only

Docker

by ofershap

MCP server for Docker — manage containers, images, volumes, and compose services from your IDE

138 installs/wk local only

Komodo MCP Server

by mp-tool

MCP server for Komodo - manage Docker containers, servers, stacks, and deployments via AI

140 installs/wk local only

MCP Sandbox Computer VM for AI — questions

Answers built from our own checks of this server.

Why is there no uptime for MCP Sandbox Computer VM for AI?

MCP Sandbox Computer VM for AI runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package mcp-sandbox-computer-vm-for-ai was installed 126 times last week.

How do I connect MCP Sandbox Computer VM for AI?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls mcp-sandbox-computer-vm-for-ai straight from pypi; nothing to host, nothing to sign up for.

How many people use MCP Sandbox Computer VM for AI?

The pypi package mcp-sandbox-computer-vm-for-ai was installed 126 times in the last week. Week over week that is -19%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is MCP Sandbox Computer VM for AI open source?

Yes — it is published under the MIT licence, written in Python and 3 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.