Skarn runs on your own machine — the client starts it, so there is no endpoint to ping. 620 installs a week from npm. Last commit 1 Sep 2026.
Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted
We read the source, 12 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.
этот файл ставится пользователю, но в репозитории его нет
const res = spawnSync(binPath, process.argv.slice(2), { stdio: "inherit" });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add skarn -- npx -y @skarn-security/skarn
{
"mcpServers": {
"skarn": {
"args": [
"-y",
"@skarn-security/skarn"
],
"command": "npx"
}
}
}
[mcp_servers.skarn]
command = "npx"
args = ["-y", "@skarn-security/skarn"]
{
"mcpServers": {
"skarn": {
"args": [
"-y",
"@skarn-security/skarn"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"skarn": {
"args": [
"-y",
"@skarn-security/skarn"
],
"command": "npx"
}
}
}
Local-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs
Scan configs, files, or text for leaked secrets and obvious misconfigurations. Nothing stored.
Manage WiseWall sites from an AI coding assistant — deploy, configure DNS, secrets, and plans.
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
Local secret & credential checks for AI-assisted dev — runs on your machine, results redacted.
Stop AI coding agents from leaking API keys. Local proxy swaps real secrets for phm_ tokens.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Local-first security check for AI coding agents: secrets, .env exposure, git-history leaks, CVEs.
Answers built from our own checks of this server.