vaultguard runs on your own machine — the client starts it, so there is no endpoint to ping. 56 installs a week from npm. Last commit 18 Sep 2026.
AI agents use your Obsidian secrets by name — values never reach their context.
What the code does
We read the source, 6 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(cmd, args, {
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 vaultguard -e 'VAULTGUARD_PASSPHRASE=<VAULTGUARD_PASSPHRASE>' -- npx -y @ashishrao-4/vaultguard{
"mcpServers": {
"vaultguard": {
"command": "npx",
"args": [
"-y",
"@ashishrao-4/vaultguard"
],
"env": {
"VAULTGUARD_PASSPHRASE": "<VAULTGUARD_PASSPHRASE>"
}
}
}
}[mcp_servers.vaultguard]
command = "npx"
args = ["-y", "@ashishrao-4/vaultguard"]
env = { VAULTGUARD_PASSPHRASE = "<VAULTGUARD_PASSPHRASE>" }{
"mcpServers": {
"vaultguard": {
"command": "npx",
"args": [
"-y",
"@ashishrao-4/vaultguard"
],
"env": {
"VAULTGUARD_PASSPHRASE": "<VAULTGUARD_PASSPHRASE>"
}
}
}
}{
"servers": {
"vaultguard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@ashishrao-4/vaultguard"
],
"env": {
"VAULTGUARD_PASSPHRASE": "<VAULTGUARD_PASSPHRASE>"
}
}
}
}Put your own value in place of
<VAULTGUARD_PASSPHRASE> (Passphrase that decrypts the encrypted secret blocks in your Obsidian vault).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
VAULTGUARD_VAULT_PATH (Path to your Obsidian vault (overrides the one in ~/.vaultguard/config.json)), VAULTGUARD_HOME (Config directory (defaults to ~/.vaultguard)), VAULTGUARD_ALLOW_GET_SECRET (Set to 1 to enable get_secret (default: disabled so values never reach the agent)).
Alternatives to vaultguard
same job, measured the same wayTeam secrets your AI agent can use but never read: encrypted in the repo, value-blind tools.
Local encrypted secret broker for AI agents: request keys by name, approve each use over MCP.
Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.
Local MCP tools for secret status and guarded deployment. Values never reach the agent.
Request and send secrets for AI agents, end-to-end encrypted and never shown in the chat.
A secret store for AI agents: the agent never sees the plaintext.
Injects secrets into shell commands at exec time; plaintext never reaches the LLM context
Credential custody for agents: use secrets blind (ssh/http/smtp/git/db), never in context.
vaultguard — questions
Answers built from our own checks of this server.