hush is answering right now. Last checked 2 min ago. It exposes 1 tools. Last commit 14 Sep 2026.
A secret store for AI agents: the agent never sees the plaintext.
We read the source, 40 min ago · tools taken from the live server · rules 3dff92dd89df
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 legacyFile = path.join(home, 'Library/LaunchAgents/com.hush-backup.plist');
const call = (exe, args, env = process.env) => spawnSync(exe, args, { env, encoding: 'utf8', timeout: 300000, maxBuffer: 1024 * 1024 });
const dir = path.join(home, base);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.
claude mcp add hush --transport http https://royashbrook.com/hush
{
"mcpServers": {
"hush": {
"url": "https://royashbrook.com/hush"
}
}
}
[mcp_servers.hush]
url = "https://royashbrook.com/hush"
{
"mcpServers": {
"hush": {
"url": "https://royashbrook.com/hush"
}
}
}
{
"mcpServers": {
"hush": {
"url": "https://royashbrook.com/hush"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_skill
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://royashbrook.com/hush | streamable-http | answering | 492 ms | 2 min ago |
Secure secrets proxy for AI agents — manages API keys so agents never see raw credentials.
Credential custody for agents: use secrets blind (ssh/http/smtp/git/db), never in context.
Local AES-256-GCM vault for AI agents. Secrets stay local, LLMs never see real API keys.
Detect and redact PII, PHI, PCI and secrets in text and files before an AI agent sees them.
Secure secret management with a Human-In-The-Loop (HITL) interceptor for agent mutations.
Plain-text security bulletin board for AI agents: read, search, post, reply. No auth to read.
Zero-knowledge MCP secrets vault for AI agents: secrets injected at runtime, never seen by the model
OS keychain secrets for AI coding agents, over MCP.
Answers built from our own checks of this server.