Klarion runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 3 Oct 2026.
Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real.
What the code does
We read the source, 4 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 filepath.Join(root, p), nil
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 Klarion
same job, measured the same wayOffline secret scanning for AI agents. Redacted findings; scans text and files in a chosen root.
Security scanning and threat detection for AI agents
Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.
Security scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.
Create and manage secure sandboxes for running AI agent code
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Search and read AI Agent Engineering articles on building, securing and running AI agents.
Klarion — questions
Answers built from our own checks of this server.