Nostr Ops MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 42 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.
Nothing serious here today
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.
Connect this server
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 -e 'NOSTR_RELAYS=<NOSTR_RELAYS>' -- npx -y nostr-ops-mcp{
"mcpServers": {
"nostr-ops-mcp": {
"command": "npx",
"args": [
"-y",
"nostr-ops-mcp"
],
"env": {
"NOSTR_RELAYS": "<NOSTR_RELAYS>"
}
}
}
}[mcp_servers.nostr-ops-mcp]
command = "npx"
args = ["-y", "nostr-ops-mcp"]
env = { NOSTR_RELAYS = "<NOSTR_RELAYS>" }{
"mcpServers": {
"nostr-ops-mcp": {
"command": "npx",
"args": [
"-y",
"nostr-ops-mcp"
],
"env": {
"NOSTR_RELAYS": "<NOSTR_RELAYS>"
}
}
}
}{
"servers": {
"nostr-ops-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"nostr-ops-mcp"
],
"env": {
"NOSTR_RELAYS": "<NOSTR_RELAYS>"
}
}
}
}Put your own value in place of
<NOSTR_RELAYS> (Comma-separated wss:// relay URLs).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
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)).
Alternatives to Nostr Ops MCP
same job, measured the same waySecurity 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.
Risk limits and an audit log for AI agents trading Hyperliquid, enforced outside the model.
Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.
Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.
Human approvals, autonomy limits and a chained audit log for the AI agents of service firms.
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Nostr Ops MCP — questions
Answers built from our own checks of this server.