Portunus runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 21 Oct 2026.
Secret broker for agents: reference secrets by name; values injected only at the execution boundary.
What the code does
We read the source, 1 d ago · rules 995398eba69f
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.
return subprocess.run(argv, capture_output=True, text=True, timeout=timeout)
env = dict(os.environ) if env is None else env
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Alternatives to Portunus
same job, measured the same wayCredential isolation for AI agents. Inject secrets at the network boundary.
Local encrypted secret broker for AI agents: request keys by name, approve each use over MCP.
Request and send secrets for AI agents, end-to-end encrypted and never shown in the chat.
Deterministic execution boundary and reference MCP sidecar for Arcstone Security Stack
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
AI agents use your Obsidian secrets by name — values never reach their context.
HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
Local, read-only, names-only secret metadata for explicitly approved stores. Never returns values.
Portunus — questions
Answers built from our own checks of this server.