keyshroud runs on your own machine — the client starts it, so there is no endpoint to ping. 601 installs a week from npm. Last commit 24 Oct 2026.
Agent-safe secrets from self-hosted Vaultwarden/Bitwarden: injected into commands, masked in output
What the code does
We read the source, 7 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.
const child = spawn(windows ? process.env.ComSpec ?? join(core.SYSTEM32, "cmd.exe") : "/bin/sh", windows ? ["/d", "/s", "/c", `"${args.command}"`] : ["-c", args.command], {
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.
Connect this server
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 keyshroud -- npx -y keyshroud{
"mcpServers": {
"keyshroud": {
"command": "npx",
"args": [
"-y",
"keyshroud"
]
}
}
}[mcp_servers.keyshroud]
command = "npx"
args = ["-y", "keyshroud"]{
"mcpServers": {
"keyshroud": {
"command": "npx",
"args": [
"-y",
"keyshroud"
]
}
}
}{
"servers": {
"keyshroud": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"keyshroud"
]
}
}
}Alternatives to keyshroud
same job, measured the same wayUnofficial MCP server for the Bitwarden Public API and Secrets Manager, self-hosted or cloud.
Bitwarden/Vaultwarden for agents: list tagged items, TOTP codes, one-time Sends, save new secrets.
Let AI agents use secrets without seeing them: inject into a command, redact the output.
Read-only access to secrets in a local KeePassXC vault. Runs commands with them injected.
Use API keys from your Keyfold vault in commands and .env files. No tool returns a secret value.
Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
Encrypted environment variable vault with AI access policies, keeping secrets safe from AI agents.
Encrypted environment variable vault with AI access policies, keeping secrets safe from AI agents.
keyshroud — questions
Answers built from our own checks of this server.