SysKnife runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 22 Sep 2026.
Administers Linux via typed, approval-gated actions with an Ed25519-signed audit trail.
What the code does
We read the source, 14 h ago · rules 3dff92dd89df
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.
const hookPath = path.join('.claude', file);
let keys_path = format!("/home/{test_user}/.ssh/authorized_keys");
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 SysKnife
same job, measured the same wayEd25519 identity for AI agents. Verify seals, sign documents, gate actions with approvals.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
Scope-gated Linear project administration with optional GitHub and Obsidian evidence adapters
Verifiable execution for AI agents: Ed25519-signed work contracts and audit trails.
Headless browser with SHA-256 audit trails and Ed25519-signed proof bundles for AI agents.
Let AI agents query and operate business systems with authorization, approval and audit trails.
Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.
SysKnife — questions
Answers built from our own checks of this server.