Sabline runs on your own machine — the client starts it, so there is no endpoint to ping. 171 installs a week from pypi. Last commit 13 Oct 2026.
Run code an AI wrote without handing it everything you can reach.
What the code does
We read the source, 2 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
done = subprocess.run(cmd, cwd=cwd, input=stdin, capture_output=True,
env = dict(os.environ)
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.
done = subprocess.run(
const child = spawn(exe, ["-c", script], {
path = os.path.join(schemas, name)
__import__(extra)
e = dict(os.environ)
for dp, dirs, names in os.walk(here):
home / ".ssh" / "id_ed25519": b"key",
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Sabline and you get told the day something new turns up.
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 mcp add sabline -- npx -y sabline-lang{
"mcpServers": {
"sabline": {
"command": "npx",
"args": [
"-y",
"sabline-lang"
]
}
}
}[mcp_servers.sabline]
command = "npx"
args = ["-y", "sabline-lang"]{
"mcpServers": {
"sabline": {
"command": "npx",
"args": [
"-y",
"sabline-lang"
]
}
}
}{
"servers": {
"sabline": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"sabline-lang"
]
}
}
}Alternatives to Sabline
same job, measured the same wayRussian APIs for AI agents: YooKassa, CDEK, Bitrix24 and more. Ready scenarios with code. No key.
Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute s…
A shared team wiki your coding agents read and write — across every repo and every MCP client.
Cloud, SaaS and AI spend in one system of record. Each saving applied for you or shipped as code.
The repo guardian AI agents handshake with before they touch your code.
Codebase understanding with exact evidence, qualified on every read and re-aligned on change.
Run Offensive360 SAST scans (60+ languages) on local code; findings with file/line and fixes
Scores your code across 12 areas, with findings, fix prompts, and re-assessment in your AI agent
Sabline — questions
Answers built from our own checks of this server.