Clotr Guard runs on your own machine — the client starts it, so there is no endpoint to ping. 291 installs a week from npm. Last commit 29 Oct 2026.
Checks text for credentials and personal details on your device, before it goes anywhere.
We read the source, 3 h ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
if (m.startsWith("https://hooks.slack.com/")) return looksRandomAnyCase(m.slice(m.lastIndexOf("/") + 1));
String.raw`\b(?<front>${FRONT})?(?<num>${HOUSE_NUM})[^\S\n]+(?:(?<pre>${DIRECTION})[^\S\n]+)?(?<name>(?:[A-Za-z0-9][\w'.-]*[^\S\n]+){0,3}?[A-Za-z0-9][\w'.-]*)[^\S\n]+(?<suf>${SUFFIX})(?:[^\S\n]+(?<post>${DIRECTION}))?(?![\w])${UNIT}`,
const prepared = spawnSync(process.execPath, [path.join(__dirname, "prepare-ui.js")], {
else if (/^[\w.-]+\.js$/.test(url)) file = path.join(root, "extension", url);
"id_rsa",
if (m.startsWith("https://hooks.slack.com/")) return looksRandomAnyCase(m.slice(m.lastIndexOf("/") + 1));
"/9j/4AAQSkZJRgABAQAAAQABAAD/4gHYSUNDX1BST0ZJTEUAAQEAAAHIAAAAAAQwAABtbnRyUkdCIFhZWiAH4AABAAEAAAAAAABhY3NwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAA9tYAAQAAAADTLQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlkZXNjAAAA8AAAACRyWFlaAAABFAAAABRnWFlaAAABKAAAABR…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check Clotr Guard every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 clotr-guard -- npx -y clotr-guard
{
"mcpServers": {
"clotr-guard": {
"command": "npx",
"args": [
"-y",
"clotr-guard"
]
}
}
}
[mcp_servers.clotr-guard]
command = "npx"
args = ["-y", "clotr-guard"]
{
"mcpServers": {
"clotr-guard": {
"command": "npx",
"args": [
"-y",
"clotr-guard"
]
}
}
}
{
"servers": {
"clotr-guard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"clotr-guard"
]
}
}
}
Check text for leaked credentials before an agent writes or commits it. Runs locally.
Deterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.
Check a document for hidden text before your agent reads it. PDF, Office, RTF, HTML.
Identity and auth for AI agents: credentials, tokens, delegations, and permission checks.
Database guardrails for AI agents: check SQL against your Vericto rules before it runs.
Read-only checks for DIDs, credentials, MCP servers, A2A cards and agent delegation.
Check emails before you send, and get a $1 SPF/DKIM/DMARC fix plan for your domain. Pay per call.
Find and redact personal data and secrets in text before it reaches a model. Local, no account.
Answers built from our own checks of this server.