Demipass runs on your own machine — the client starts it, so there is no endpoint to ping. 74 installs a week from npm. Last commit 14 Aug 2026.
Credential custody for agents: use secrets blind (ssh/http/smtp/git/db), never in context.
Today is the operative word: we check Demipass 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 demipass -- npx -y demipass
{
"mcpServers": {
"demipass": {
"args": [
"-y",
"demipass"
],
"command": "npx"
}
}
}
[mcp_servers.demipass]
command = "npx"
args = ["-y", "demipass"]
{
"mcpServers": {
"demipass": {
"args": [
"-y",
"demipass"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"demipass": {
"args": [
"-y",
"demipass"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
DEMIPASS_TOKEN (Dustforge JWT bearer token. Self-onboard at https://dustforge.com/.well-known/silicon or mint via the 2FA email flow.), DEMIPASS_URL (API base URL (default https://api.dustforge.com)).
The author declared them in the registry entry; get the values from the project itself.
A secret store for AI agents: the agent never sees the plaintext.
Encrypted secrets and credential management for agents
Credential isolation for AI agents. Inject secrets at the network boundary.
Secure secrets proxy for AI agents — manages API keys so agents never see raw credentials.
Encrypted secrets vault for AI agents — secrets resolved at runtime, never seen by LLMs.
Check text for leaked credentials before an agent writes or commits it. Runs locally.
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
Secrets for developers and agents—secure context and workflows without exposing secret values.
Answers built from our own checks of this server.