Sandboxer runs on your own machine — the client starts it, so there is no endpoint to ping.
Cloud Linux VMs for your agent: run code, Docker, files and HTTPS previews in a Sandboxer microVM.
Today is the operative word: we check Sandboxer every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 -- npx -y sandboxer-mcp
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"sandboxer-mcp"
]
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "sandboxer-mcp"]
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"sandboxer-mcp"
]
}
}
}
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"sandboxer-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
SANDBOXER_API_KEY (Sandboxer API key (create one on the dashboard under API keys). Optional if you signed in with `sbx login`).
Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.
Disposable Firecracker microVM sandboxes for agents: run code, snapshot, fork. Needs Linux with KVM.
Hand Rush a task: an agent does the work in its own cloud sandbox and returns a PR, report or files.
Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.
Create and manage secure sandboxes for running AI agent code
Give your agent a persistent workspace: files, a code sandbox and a public URL to publish to.
Offline docs-as-code for any backend and frontend: a MkDocs site in your repo, by your AI agent.
Code mode (preview): the AI writes a script against a typed foundry.* API and runs it in a sandbox.
Answers built from our own checks of this server.