vaultguard runs on your own machine — the client starts it, so there is no endpoint to ping. 138 installs a week from npm.
AI agents use your Obsidian secrets by name — values never reach their context.
Today is the operative word: we check vaultguard 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 vaultguard -- npx -y @ashishrao-4/vaultguard
{
"mcpServers": {
"vaultguard": {
"args": [
"-y",
"@ashishrao-4/vaultguard"
],
"command": "npx"
}
}
}
[mcp_servers.vaultguard]
command = "npx"
args = ["-y", "@ashishrao-4/vaultguard"]
{
"mcpServers": {
"vaultguard": {
"args": [
"-y",
"@ashishrao-4/vaultguard"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"vaultguard": {
"args": [
"-y",
"@ashishrao-4/vaultguard"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
VAULTGUARD_PASSPHRASE (Passphrase that decrypts the encrypted secret blocks in your Obsidian vault.), 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).).
The author declared them in the registry entry; get the values from the project itself.
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.
A secret store for AI agents: the agent never sees the plaintext.
Zero-knowledge MCP secrets vault for AI agents: secrets injected at runtime, never seen by the model
Credential custody for agents: use secrets blind (ssh/http/smtp/git/db), never in context.
Encrypted secrets vault for AI agents — secrets resolved at runtime, never seen by LLMs.
Local AES-256-GCM vault for AI agents. Secrets stay local, LLMs never see real API keys.
Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.
Answers built from our own checks of this server.