vaultguard MCP server

🔐 vaultguard Your Obsidian vault, guarded for your AI agents. npx @ashishrao-4/vaultguard init · zero dependencies · pure Node · cross-platform

The problem

Your AI agents are powerful. They ship code, run commands, and one day they will ask: "give me the database URL."

You hand it over. Now that value lives in every transcript, log, checkpoint, and backup of your conversations. Rotate it a month later — a year later — and the old one is still out there.

The vault itself — Obsidian — is encrypted only if you make it so, and your agent reading your notes means your agent reading your secrets.

What vaultguard does

Secrets live in your Obsidian vault as AES-256-GCM ciphertext. Your agents get them by name over MCP — they run commands with the values injected into the environment and never see them, while every access is audited.

The simple version: your agent asks by name, vaultguard decrypts on demand, the value stays out of the conversation.

• You own the data. No cloud, no SaaS, no server. The encrypted blocks are plain markdown.
• Readable in Obsidian. Encrypted blocks look like notes; reveal them with one click.
• Tell your agent to run things using secrets — values never surface in transcripts.
• Zero npm dependencies. Pure Node ≥ 18. Windows / macOS / Linux.

Quickstart

1 · Install

npm install -g @ashishrao-4/vaultguard

2 · Point it at your vault

vaultguard init --vault "C:\Users\you\Documents\Obsidian Vault"

It asks for a passphrase — the key that encrypts and decrypts every block in this vault. Then it:

• creates Secrets.md in your vault,
• installs the Inline Secret Block plugin into the vault automatically,
• writes ~/.vaultguard/config.json — without the passphrase (you provide it via VAULTGUARD_PASSPHRASE).

Restart Obsidian and enable the plugin: Settings → Community plugins → Inline Secret Block → Enable.

The passphrase is never written to disk by default. Prefer env vars:

VAULTGUARDPASSPHRASE (or DOORMANPASSPHRASE). If you want it conveniently stored anyway —

at the cost of weaker security — run vaultguard init --store-passphrase instead (see Threat model).

3 · Add your first secret — the Obsidian way

In Obsidian, open Secrets.md and add a plaintext block:

Mydatabaseurl@postgres

Click Show — the plugin instantly replaces it with an encrypted secret-lock block. Your raw value is gone; what remains:

Nx60U4Ph/+1CO+58Zr00HXhEW9GZ6voHlpS+bEXPpP69avbJaSfafZCC2dpPn6UgdMN+3PJUd+UPm39YAXhFTbHvLUpHDndzbODsL8fOm7IMWC16zjSQCW7CbRWklmUxOGl0lX2qpQ==

That's it. Same value, later, forever: click Show again.

No Obsidian? Use the CLI instead:

bash

vaultguard add DB_URL # hidden prompt

vaultguard set DB_URL # rotate in place

4 · Connect your agent

vaultguard mcp

prints ready-made config for your harness:

opencode — in opencode.json (or globally via the app):

{
  "mcp": {
    "vaultguard": {
      "type": "local",
      "command": ["node", "C:/path/to/vaultguard/src/server.mjs"],
      "environment": { "VAULTGUARD_PASSPHRASE": "your-passphrase" }
    }
  }
}

Claude Code:

claude mcp add vaultguard -e VAULTGUARD_PASSPHRASE=your-passphrase -- node C:/path/to/vaultguard/src/server.mjs

Shortened. The full README is on GitHub.