Sandbox as a Service

Give an AI agent an isolated Linux VM: create a sandbox, run commands, transfer files, expose an HTTPS preview, and destroy it when finished.

CommunityOnlineAPI key requiredGlobalFreeCan modify data

What it can do

  • Create Sandbox: Create an isolated cloud sandbox — a dedicated virtual machine you can run commands in. Returns once the sandbox is ready. Python 3, Node.js 22, git and a build toolchain are pre-insta
  • Run Command: Run a shell command inside a sandbox and wait for it to finish. Returns stdout, stderr and the exit code. The command runs as an unprivileged user in /workspace. A non-zero exit code is r
  • Write File: Write a file inside a sandbox. Use this to place a script or input data before running it. Paths are relative to /workspace unless absolute. Content of any kind is safe — it is transferred

What data it sees

Do you need an account

An API key from the service settings is required

Give an AI agent an isolated Linux VM: create a sandbox, run commands, transfer files, expose an HTTPS preview, and destroy it when finished. Connect remotely over Streamable HTTP using your own Sandbox as a Service API key; no local MCP installation required. Public service information is available without a key. Account and execution tools require authentication. VM runtime uses your account credit; startup time depends on capacity. See the homepage for current pricing and limits.

How to connect

How to connect Sandbox as a Service to Claude

The server address to paste into Claude settings:

https://sandbox-as-a-service--florian-standhartinger.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Sandbox as a Service to ChatGPT

The server address to paste into ChatGPT settings:

https://sandbox-as-a-service--florian-standhartinger.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Sandbox as a Service to Cursor

The server address to paste into Cursor settings:

https://sandbox-as-a-service--florian-standhartinger.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (12)

Raw names from tools/list. Only developers need these.

create_sandboxCreate an isolated cloud sandbox — a dedicated virtual machine you can run commands in. Returns once the sandbox is ready. Python 3, Node.js 22, git and a build toolchain are pre-installed. The sandbox is destroyed automatically after timeout_minutes; nothing inside it survives that. Use this before running any code you would not want to run on the local machine.
run_commandRun a shell command inside a sandbox and wait for it to finish. Returns stdout, stderr and the exit code. The command runs as an unprivileged user in /workspace. A non-zero exit code is returned normally, not as an error. Use this to execute code, install packages, clone repositories or inspect the filesystem. To start something that keeps running (a web server), background it with `&` AND pass `cwd` instead of writing `cd ... &&` — a `&` after a `&&` list backgrounds a subshell that holds the output stream open, so the call waits out the whole timeout and returns exit_code 124. The process survives either way; only the waiting is wasted.
write_fileWrite a file inside a sandbox. Use this to place a script or input data before running it. Paths are relative to /workspace unless absolute. Content of any kind is safe — it is transferred verbatim, not interpreted by a shell.
read_fileRead a file back out of a sandbox — an artifact your code produced, a log, a generated report. Use encoding "base64" for binary files such as images.
list_filesList the contents of a directory in a sandbox, with the type and size of each entry. Defaults to /workspace. Use this to find what your code produced before reading it.
expose_portGive a server running inside the sandbox a public https URL, so a person can open it in a browser. Use this after starting a web server or dev server in the background with run_command (background it with `&` and pass `cwd` rather than `cd ... &&`). The server only needs to listen on localhost. Returns a URL that works until the sandbox is destroyed.
get_sandboxGet the current status and details of one sandbox, including when it expires.
list_sandboxesList the sandboxes on this account, newest first. Use it to find sandboxes you created earlier.
extend_sandboxPush a sandbox’s expiry further out so long-running work is not cut off. Total lifetime is still capped at 24 hours from creation.
destroy_sandboxDestroy a sandbox and stop billing for it. Everything inside is lost. Call this as soon as you are finished — do not leave sandboxes running.
get_usageShow the account’s remaining credit balance and recent sandbox usage.
get_service_infoDescribe this service: what a sandbox costs, which machine sizes exist, the account limits, and where to get an API key. Free — it never provisions anything and is not charged for. Every other tool here needs an API key and acts on the account that key belongs to.