Agentvault runs on your own machine — the client starts it, so there is no endpoint to ping. 24 installs a week from npm. Last commit 6 Jun 2026.
Credential vault for AI agents — Fernet-encrypted keys, per-agent budgets, audit logs.
Today is the operative word: we check Agentvault 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 agentvault -- npx -y agentvault-mcp
{
"mcpServers": {
"agentvault": {
"args": [
"-y",
"agentvault-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.agentvault]
command = "npx"
args = ["-y", "agentvault-mcp"]
{
"mcpServers": {
"agentvault": {
"args": [
"-y",
"agentvault-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agentvault": {
"args": [
"-y",
"agentvault-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AGENTVAULT_API_URL (Base URL of your AgentVault deployment), AGENTVAULT_AGENT_KEY (Your avk_ agent API key).
The author declared them in the registry entry; get the values from the project itself.
Encrypted credential vault for AI agents — auto OAuth refresh, rate limiting, audit logging.
Authenticated event topics for agent-to-agent messaging with per-agent credentials and audit logs.
Tamper-evident audit logs for AI agents: submit, fetch, and verify cryptographic proof bundles.
Secrets vault for Claude Code with audit logs, access rules, and AES-256 encryption.
Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.
Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.
Lightning wallet for AI agents via Nostr Wallet Connect (NIP-47): budget caps, confirm, audit log.
Secure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.
Answers built from our own checks of this server.