Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Lightning trust + audit oracle. Score, pay, and audit L402 endpoints with Ed25519 receipts.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
SATRANK_API_BASEYou need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"satrank": {
"command": "npx",
"args": [
"-y",
"satrank-mcp"
],
"env": {
"SATRANK_API_BASE": "your-value"
}
}
}
}Run this in your terminal
claude mcp add satrank --env SATRANK_API_BASE=your-value -- npx -y satrank-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"satrank": {
"command": "npx",
"args": [
"-y",
"satrank-mcp"
],
"env": {
"SATRANK_API_BASE": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"satrank": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"satrank-mcp"
],
"env": {
"SATRANK_API_BASE": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
SATRANK_API_BASE envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain satrank.dev (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.0.1) reached the registry 6 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, SwarmMemo
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Talk with agent swarms: rooms, private messages and paid tasks for AI agents
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Lightning trust oracle for AI agents on L402. Bitcoin-pure.
POST /api/intent (paid 2 sats via L402): an agent passes a category + budget + SLA, gets back the top-K endpoints with full Bayesian breakdown.Doc surfaces:
GET / landing page (static HTML)
GET /methodology technical reference (static HTML) GET /api API reference (static HTML) GET /openapi.json OpenAPI 3.0 spec (machine-readable)
Functional API (nine routes — POST /api/intent is the only L402-gated one):
POST /api/intent paid, 2 sats via L402
POST /api/deposit free, mint a multi-use deposit macaroon (10–10000 sats, 30-day TTL) GET /api/deposit/:macaroon_id free, read remaining balance GET /api/services/:url_hash free, per-endpoint score snapshot GET /api/services/categories free, list of catalogue categories GET /api/services/best free, top-3 per category (5-min cache) GET /api/oracle/budget free, last 24h revenue + paid-probe spend GET /health free, liveness GET /.well-known/satrank-key free, oracle pubkey for offline verify
Deposit macaroons let an agent pre-pay N sats once and use the bearer preimage across many /api/intent calls without a Lightning round-trip per call. Authorization: L402 deposit_ : .
Three tools for any MCP-compatible AI runtime (Claude Code, Cursor, Codex, n8n):
intent forwards POST /api/intent (paid)
get_endpoint_score forwards GET /api/services/:url_hash (free) verify_assertion offline Schnorr verification of kind 30782 (no network)
Install in Claude Code:
claude mcp add satrank -- npx -y satrank-mcp
Self-hosters point SATRANK_API_BASE at their own deployment.
14 source files + 4 doc surfaces (3 HTML pages + OpenAPI spec). Read top-to-bottom in 30 minutes.
src/
├── types.ts Stage, Posterior, Endpoint, Observation ├── config.ts zod env schema, parsed once at boot ├── logger.ts JSON-line stdout ├── db.ts pg Pool + idempotent schema bootstrap ├── schema.sql 9 tables in ONE file (no migrations folder) ├── lnd.ts minimal LND REST client (addInvoice + payInvoice) ├── ssrf.ts RFC1918 + link-local + IPv6 ULA URL guard ├── nostr.ts kind 30782 sign + publish + offline verify ├── scoring.ts Beta(α,β) per stage, Wilson CI95, ranker ├── probe.ts HTTP probe with optional L402 pay ├── crawler.ts l402.directory + RSS + DNS + cron ├── api.ts Express; 9 functional routes + 4 doc surfaces, native L402 paid gate, deposit credits ├── mcp.ts MCP server, 3 tools, ships verbatim to npm ├── landing.html static landing served at GET / ├── methodology.html technical reference served at GET /methodology ├── api-reference.html API reference served at GET /api ├── openapi.json OpenAPI 3.0 spec served at GET /openapi.json └── index.ts boot + shutdown
cp .env.example .env
npm install npm run build npm start
For paid probes + paid /api/intent gate, set LND_REST_URL + LND_MACAROON_HEX + L402_MACAROON_SECRET. For Nostr trust assertions, set NOSTR_PRIVATE_KEY.
For each (endpoint, stage), maintain a Beta(α, β) posterior with α₀ = β₀ = 1 (uniform prior). On every observation:
Stage mean: α / (α+β). 95% credible interval via Wilson (closed-form). End-to-end success: ∏ stage_means across the 5 stages, assuming stage independence.
is_meaningful is true iff the challenge stage has at least MEANINGFUL_N_OBS_MIN observations. The challenge stage is observed on every probe (free or paid), so its n_obs converges fastest. p_e2e remains the honest end-to-end product separately.
AGPL-3.0