Nwc MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 36 installs a week from npm. Last commit 15 Jun 2026.
Lightning wallet for AI agents via Nostr Wallet Connect (NIP-47): budget caps, confirm, audit log.
Today is the operative word: we check Nwc MCP 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 nwc-mcp -- npx -y nwc-mcp
{
"mcpServers": {
"nwc-mcp": {
"args": [
"-y",
"nwc-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.nwc-mcp]
command = "npx"
args = ["-y", "nwc-mcp"]
{
"mcpServers": {
"nwc-mcp": {
"args": [
"-y",
"nwc-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"nwc-mcp": {
"args": [
"-y",
"nwc-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
NWC_CONNECTION_STRING (Nostr Wallet Connect connection string (nostr+walletconnect://...)), NWC_DAILY_BUDGET_SATS (Daily spend cap in sats), NWC_READ_ONLY (Set true to block all spend tools).
The author declared them in the registry entry; get the values from the project itself.
Nostr publishing, queries, and DMs for AI agents, with allowlists, rate limits, and an audit log.
Credential vault for AI agents — Fernet-encrypted keys, per-agent budgets, audit logs.
Safe Google Workspace admin for AI agents: read-only by default, confirm-gated deletes, audit log.
Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.
X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant.
X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant.
Secure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.
Encrypted credential vault for AI agents — auto OAuth refresh, rate limiting, audit logging.
Answers built from our own checks of this server.