MCP Sandbox Computer VM for AI runs on your own machine — the client starts it, so there is no endpoint to ping. 104 installs a week from pypi. Last commit 31 Aug 2026.
Named Docker and Fly Machine sandbox computers with an interactive MCP App dashboard.
We read the source, 13 h ago · rules 3dff92dd89df
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.
async def exec(self, request: ExecRequest) -> ExecResult:
result = subprocess.run([engine, "info"], capture_output=True, text=True)
- /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.
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.
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 mcp add mcp-sandbox-computer-vm-for-ai -- uvx mcp-sandbox-computer-vm-for-ai
{
"mcpServers": {
"mcp-sandbox-computer-vm-for-ai": {
"args": [
"mcp-sandbox-computer-vm-for-ai"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-sandbox-computer-vm-for-ai]
command = "uvx"
args = ["mcp-sandbox-computer-vm-for-ai"]
{
"mcpServers": {
"mcp-sandbox-computer-vm-for-ai": {
"args": [
"mcp-sandbox-computer-vm-for-ai"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-sandbox-computer-vm-for-ai": {
"args": [
"mcp-sandbox-computer-vm-for-ai"
],
"command": "uvx"
}
}
}
MCP server for managing Fly.io machines, apps, logs, and Docker images.
Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents
MCP server for real interactive terminal sessions — REPLs, SSH, databases, Docker
Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.
Self-hosted homelab dashboard with a built-in read-only MCP server (hosts, Docker, GPU, services).
MCP server for Docker — manage containers, images, volumes, and compose services from your IDE
MCP server for Komodo - manage Docker containers, servers, stacks, and deployments via AI
Docker for AI agents — containers, compose stacks, logs and databases, locally or over SSH.
Answers built from our own checks of this server.