Helmsman runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 5 Nov 2026.
Adaptive instruction server: serves agent instructions and skills tuned to the calling model
What the code does
We read the source, 21 h 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.
if Path::new("/.dockerenv").exists() {
let specific = self.repo_path.join(format!("{}.{}", sub, SKILL_EXTENSION));
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 Helmsman
same job, measured the same wayCheck any MCP server or agent skill before installing: upkeep, real adoption, and OSV advisories.
Chipp: hosted integrations and their catalog, and MCP servers connected to an agent
Scan MCP servers for tool poisoning, hidden instructions and silent tool changes. Runs on Apify.
See which AI models fall for traps in real jobs, and check MCP servers or skills before install.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Search, fetch, lint, and install Agent Skills (SKILL.md) from the SkillMD registry.
A true MCP server where the agent is the model and the API key. No API keys.
Toolbox for AI agent skills: scaffold, lint, pack, install, and serve SKILL.md skills
Helmsman — questions
Answers built from our own checks of this server.