This is a secret scanner focused on catching credential leaks before they escape into commits, logs, or production environments. The source details are minimal, but the value proposition is clear: it's designed to scan for corporate API keys, tokens, and other sensitive strings that shouldn't be exposed. You'd reach for this when you need an extra layer of protection in your development workflow, particularly in environments where multiple developers are touching code that interacts with external services. It runs as a remote SSE transport, so it can plug into your Claude setup without local installation. Think of it as a pre-commit guard rail, catching AWS keys, database credentials, and OAuth tokens before they become security incidents.
claude mcp add --transport sse io.github.evozim-vaultguard https://vaultguard-mcp.vercel.app/api/mcp