Nostr Ops 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.
Nostr publishing, queries, and DMs for AI agents, with allowlists, rate limits, and an audit log.
Today is the operative word: we check Nostr Ops 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 nostr-ops-mcp -- npx -y nostr-ops-mcp
{
"mcpServers": {
"nostr-ops-mcp": {
"args": [
"-y",
"nostr-ops-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.nostr-ops-mcp]
command = "npx"
args = ["-y", "nostr-ops-mcp"]
{
"mcpServers": {
"nostr-ops-mcp": {
"args": [
"-y",
"nostr-ops-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"nostr-ops-mcp": {
"args": [
"-y",
"nostr-ops-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
NOSTR_RELAYS (Comma-separated wss:// relay URLs), NOSTR_NIP46_URI (NIP-46 bunker URI (preferred signer; keeps the nsec off this machine)), NOSTR_PRIVATE_KEY (nsec private key (alternative to NOSTR_NIP46_URI; read-only mode if neither is set)), NOSTR_ALLOWED_KINDS (Comma-separated event kinds the server may publish (required when a signer is configured)).
The author declared them in the registry entry; get the values from the project itself.
Security gate for agent-driven WhatsApp: allowlist, secret scan, rate limit, audit log.
Lightning wallet for AI agents via Nostr Wallet Connect (NIP-47): budget caps, confirm, audit log.
Encrypted credential vault for AI agents — auto OAuth refresh, rate limiting, audit logging.
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
PublishReady: Deterministic writing control with local-first metrics and AI prose audits.
Authenticated event topics for agent-to-agent messaging with per-agent credentials and audit logs.
Process management and monitoring for AI agents with strict security boundaries
Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.
Answers built from our own checks of this server.