fcvm runs on your own machine — the client starts it, so there is no endpoint to ping. 159 installs a week from pypi. Last commit 20 Oct 2026.
Disposable Firecracker microVM sandboxes for agents: run code, snapshot, fork. Needs Linux with KVM.
We read the source, 4 d ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
if (setgroups(ng, groups) < 0 || setgid(gid) < 0 || setuid(uid) < 0) {
subprocess.run(["mkfs.ext4", *opts, "-d", root, *rest], check=True)
proc = subprocess.Popen(args.cmd, stdin=slave, stdout=slave, stderr=slave, start_new_session=True)
subprocess.run(args.on_exit, shell=True, env=env)
link = os.path.join(args.link_dir, name)
async def exec(self, name, d):
exec(command: string | undefined, opts?: ExecOptions & { background?: false }): Promise<ExecResult>;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check fcvm 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 fcvm -- uvx fcvm-mcp
{
"mcpServers": {
"fcvm": {
"command": "uvx",
"args": [
"fcvm-mcp"
]
}
}
}
[mcp_servers.fcvm]
command = "uvx"
args = ["fcvm-mcp"]
{
"mcpServers": {
"fcvm": {
"command": "uvx",
"args": [
"fcvm-mcp"
]
}
}
}
{
"servers": {
"fcvm": {
"type": "stdio",
"command": "uvx",
"args": [
"fcvm-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
FCVM_MCP_NETWORK (Pin the network policy for every sandbox: none, or an allowlist such as @pypi,@github), FCVM_MCP_TEMPLATE (Template used when the agent names neither an image nor a template, e.g. python-sandbox), FCVM_MCP_TTL (Stop sandboxes this long after boot unless the agent sets a lifetime, e.g. 4h), FCVM_MCP_IDLE_STOP (Stop sandboxes that saw no exec or file operation for this long, e.g. 30m), FCVM_MCP_SECRETS (Names of environment variables passed into every sandbox as secrets, e.g. GITHUB_TOKEN), FCVM_MCP_FORWARD (Host credentials relayed into every sandbox: ssh-agent, git), FCVM_MCP_CACHE (1: restricted sandboxes fetch pip and npm packages through the host's mirror), FCVM_MCP_JAIL (0: don't run sandboxes under the Firecracker jailer even when it is set up), FCVM_BIN (Path of the fcvm command, when it isn't on PATH, in ~/.local/bin or in /usr/local/bin).
Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.
Cloud Linux VMs for your agent: run code, Docker, files and HTTPS previews in a Sandboxer microVM.
Disposable email inboxes for AI agents: create an address, wait for mail, read OTP codes and links.
Disposable email for agents: create an inbox, wait for the message, read the code. No key needed.
Disposable inboxes for AI agents: create an address, wait for the email, get the code or link.
Disposable email addresses for tests and agents: register, wait for mail, extract codes and links.
Disposable email inboxes for AI agents: create, wait for mail, extract verification codes
Disposable email inboxes for AI agents — read messages and verification codes.
Answers built from our own checks of this server.