Server data from the Official MCP Registry
Lightning wallet for AI agents via Nostr Wallet Connect (NIP-47): budget caps, confirm, audit log.
Lightning wallet for AI agents via Nostr Wallet Connect (NIP-47): budget caps, confirm, audit log.
This is a well-architected Lightning wallet MCP server with a defense-in-depth safety model. The code demonstrates strong security practices: multi-layer safety gates (read-only mode, allowlist, budget caps, two-step confirmation), proper input validation, structured audit logging, and secure credential handling via environment variables. Permissions are appropriate for its purpose. Minor code quality issues around error handling and test coverage do not materially impact security. Supply chain analysis found 5 known vulnerabilities in dependencies (2 critical, 2 high severity). Package verification found 1 issue.
7 files analyzed · 11 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: NWC_CONNECTION_STRING
Environment variable: NWC_DAILY_BUDGET_SATS
Environment variable: NWC_READ_ONLY
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-llmops-pro-nwc-mcp": {
"env": {
"NWC_READ_ONLY": "your-nwc-read-only-here",
"NWC_CONNECTION_STRING": "your-nwc-connection-string-here",
"NWC_DAILY_BUDGET_SATS": "your-nwc-daily-budget-sats-here"
},
"args": [
"-y",
"nwc-mcp"
],
"command": "npx"
}
}
}From the project's GitHub README.
A Lightning wallet for your LLM agent. MCP server that exposes Nostr Wallet Connect (NIP-47) wallet operations as tools your agent can call — read balance, generate invoices, pay invoices, pay Lightning Addresses, pay LNURLs, batch payments, keysend — all wrapped in a defense-in-depth safety stack.
Drop it into Claude Desktop, Claude Code, Cursor, or any MCP-speaking client. Hand the agent a sub-wallet (not your main one). Set a daily cap. Let it spend sats on your behalf within rails you control.
v0.2 — all spend tools shipped. Twelve tools (7 read/receive + 5 spend + 1 confirm), four safety gates, full audit log. Validated end-to-end against Alby Hub + Olympus by ZEUS routing — real outbound payment settled in 8 seconds.
The safety stack is the load-bearing reason this is usable in production: the agent can request a payment, but the server refuses anything that breaches your configured limits, demands a second-step confirmation if you set one, and writes every call to a structured audit log.
| Tool | Purpose |
|---|---|
nwc_get_info | Wallet capabilities, supported NIP-47 methods, node pubkey, network, alias. Call first. |
nwc_get_balance | Spendable balance in sats (and msat). |
nwc_lookup_invoice | Look up an invoice by payment hash or bolt11; returns state + preimage if settled. |
nwc_list_transactions | List transactions with filters (time range, direction, unpaid). |
nwc_decode_invoice | Parse a bolt11 locally — amount, memo, expiry, payee pubkey. No network call. |
nwc_budget_status | Current spend budget state — daily spent, caps, lifetime spent. |
| Tool | Purpose |
|---|---|
nwc_make_invoice | Create a bolt11 invoice for a given amount of sats. |
| Tool | Purpose |
|---|---|
nwc_pay_invoice | Pay a bolt11. Amount-resolution for amountless invoices via amount_override_sats. |
nwc_pay_lightning_address | Pay name@domain.tld (LUD-16). Direct LNURL-pay resolution, non-proxied by default. |
nwc_pay_lnurl | Pay a raw lnurl1... bech32 string (LUD-01). |
nwc_multi_pay_invoice | Pay up to 20 invoices in one call. Sum is checked against the budget cap atomically. |
nwc_pay_keysend | Spontaneous payment direct to a pubkey. Default-off — opt in via NWC_KEYSEND_ENABLED=true. |
nwc_confirm_payment | Execute a two-step-confirm payment by consuming its one-time token. |
The canonical buyer setup is Alby Hub PRO with a dedicated sub-wallet for the agent — that's what this server has been smoke-tested against. But the protocol is wallet-agnostic; anything that speaks NIP-47 works.
# From npm (once published)
npx -y nwc-mcp
# From source
git clone <repo>
cd nwc-mcp
corepack enable pnpm
pnpm install
pnpm build
Copy .env.example to .env and fill in your NWC connection string:
cp .env.example .env
# edit .env: NWC_CONNECTION_STRING=nostr+walletconnect://...
The server auto-loads .env from the current working directory and from the project root (one level up from dist/). Env vars passed by the parent process (e.g., claude mcp add --env ...) take precedence over .env. .env is gitignored — keep your NWC string out of any committed file.
| Var | Purpose |
|---|---|
NWC_CONNECTION_STRING | nostr+walletconnect://... — get this from your wallet (in Alby Hub: Sub-wallets → Connections). Treat as a secret — anyone holding it can spend up to the daily cap. |
NWC_DAILY_BUDGET_SATS | Rolling 24h spend cap. Server refuses to start without this set. |
| Var | Default | Purpose |
|---|---|---|
NWC_TOTAL_BUDGET_SATS | unset | Lifetime spend cap. |
NWC_MAX_INVOICE_SATS | unset | Per-payment cap. |
NWC_READ_ONLY | false | If true, disables all spend tools — useful for dev / eval / curious mode. |
NWC_REQUIRE_CONFIRM | false | If true, spend tools return a one-time token; payment only executes after nwc_confirm_payment with the token. Trades agent autonomy for safety. |
NWC_KEYSEND_ENABLED | false | Opt-in toggle for nwc_pay_keysend. Off because keysend is power-user (no payment hash, weaker safety surface than bolt11). |
NWC_ALLOWED_DESTINATIONS | unset | Comma-separated allowlist of LN addresses / pubkeys / LNURLs. If set, ONLY those can be paid. |
NWC_LOG_PATH | ./nwc-mcp.log | Path to the structured audit log file. |
NWC_BUDGET_STATE_PATH | ./nwc-mcp-state.json | Path to the persisted budget tracker state. |
From this directory:
claude mcp add nwc -s project node "$(pwd)/dist/index.js"
This writes a .mcp.json in the project root. Project-scoped servers load only when Claude Code starts from this directory tree. Use /mcp inside a session to inspect what's loaded. Restart the CLI to pick up a fresh dist/index.js after a rebuild.
Switch -s project to -s user if you want the server available everywhere.
See examples/claude-desktop-config.json for the manifest snippet. Copy it into your client's config, replace the path placeholder. Because the server loads .env itself, you don't need to pass NWC_* vars through the client config — leave the env block empty.
This server is designed for use by autonomous LLM agents that hold the keys to spend real sats. The defense in depth runs in this order on every spend tool call:
NWC_READ_ONLY gate — if set, blocks at the first gate. No decode, no network, audit log entry only.NWC_ALLOWED_DESTINATIONS is set, the payee (pubkey for bolt11, LN address for LUD-16, LNURL string for LUD-01, pubkey for keysend) must match. Empty allowlist = no-op.NWC_BUDGET_STATE_PATH.NWC_REQUIRE_CONFIRM=true, returns a 16-byte hex token with 5-minute TTL instead of executing. Agent must call nwc_confirm_payment with the token. Safety re-runs on consume.The floor is your NWC connection's own daily cap, set in your wallet. This server's checks are belt-and-suspenders on top — if you trust nothing about the server, the wallet still won't spend past its connection-level cap.
Independent of what the LLM tells you, tail the audit log:
tail -n 5 nwc-mcp.log
Successful call: {"ts":"...","tool":"nwc_pay_invoice","outcome":"ok","result":{"paid_sats":50,...}}. Blocked: {"ts":"...","tool":"nwc_pay_invoice","outcome":"blocked","blocked_reason":"..."}. The audit log is append-only by intent; rotate it as part of your operational hygiene.
pnpm typecheck # tsc --noEmit
pnpm test # 25 vitest cases covering Allowlist, ConfirmStore, evaluateSafety, decodeLnurl
pnpm build # produces dist/index.js (~47 KB ESM bundle)
evaluateSafety is a pure function that the unit tests exercise across the full safety matrix (read-only / amount-conflict / allowlist / budget / confirm) without touching a real wallet.
For end-to-end smoke testing against a live wallet, see paywall-mcp-test/ in the parent project — a throwaway second MCP server that exposes one paid tool (premium_compliment) and validates the full agent → invoice → pay → redeem loop.
MIT — see LICENSE.
Built by LLMOps.Pro.
npub1hdg932jvwc3jdvkqywgqv0ue4nn60exrf92asy8mtazt3hjg7d2s2yw0nw — follow, DM, zap.sovereigncitizens@getalby.com — for support zaps and "this was useful" tips.Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.