Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
iOS App Store revenue and download estimates with confidence labels, for any app by name or id.
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.
You 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": {
"appworth": {
"command": "npx",
"args": [
"-y",
"@reneturcios/appworth",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add appworth -- npx -y @reneturcios/appworth mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"appworth": {
"command": "npx",
"args": [
"-y",
"@reneturcios/appworth",
"mcp"
]
}
}
}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": {
"appworth": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/appworth",
"mcp"
]
}
}
}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.
These 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 with the GitHub account CloudCorpRecords, which owns the repo
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 (0.1.0) reached the registry 3 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Tools MCP
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.
Web production tools for AI agents: contrast, JP text, WebP, JSON-LD, slugs, dates and 40+ more
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.
How much is that app worth? appworth is a small client for the App Dex service, which estimates iOS App Store revenue and downloads for any app — by name or by numeric App Store id — and labels every figure with how much it should be trusted instead of presenting a modelled number as a measured fact.
An estimate comes back with a confidence label. In our own words: a *verified* figure was reported by a real data layer rather than modelled; a *calibrated* figure was modelled but then adjusted against verified panel data for apps in the same revenue class; a *modeled* figure rests on limited public signal and should be read directionally — the range matters more than any single point inside it. Figures are gross (before store commission) unless stated otherwise, are recomputed nightly, and cover the iOS App Store only. Lookups are single-app by design; there is no bulk export.
Responses come back exactly as the service returned them: nothing is trimmed, renamed or summarised on the way through. For example, an upstream reply for Duolingo looks like:
app: Duolingo: Language Lessons
category: Education monthly_revenue: $48.0M – $48.0M monthly_downloads: 5.0M – 5.0M confidence: calibrated report_url: https://app-dex.com/a/duolingo-language-lessons-570060128
The API key is optional. The original project's configuration table calls APPDEX_API_KEY "Required", but its install prose pins the actual behaviour, and behaviour governs here: without a key the server still works — 2 requests/day, so you can try it first. A free key raises that to 5 requests/day. When a key is set it is sent on every request as Authorization: Bearer ; when it is unset, requests simply carry no Authorization header and that is never an error.
| Env var | Default | Notes |
|---|---|---|
APPDEX_API_KEY | — | Optional (see above). Sent as a Bearer token when set. |
APPDEX_API_URL | https://app-dex.com | Override only for self-hosted/staging. |
APPDEX_TIMEOUT_MS | 15000 | Request timeout (ours); a timeout is a fetch failure. |
APPINTEL_API_KEY / APPINTEL_API_URL are still read as fallbacks for older setups: each is used only when the corresponding APPDEX_* variable is unset.
estimate_app — monthly revenue + downloads for one iOS app, with a confidence label. Accepts an app name (app) or a numeric App Store id.search_apps — resolves a name (query) to App Store ids, with no figures — use it to find the id to feed estimate_app.An upstream non-2xx reply fails with appdex error: HTTP and an unreachable service (including a timeout) with appdex unreachable.
The original project's README pins the two tools, the worked estimate example, the configuration variables and the key-optional behaviour — but not the request paths or the Authorization header shape. Those are reconstructions, labelled as such:
GET /api/estimate?app= (used by estimate_app).GET /api/search?q= (used by search_apps).Authorization: Bearer header shape when a key is set.Each tool is a subcommand taking one JSON argument string:
npx @reneturcios/appworth estimate_app '{"app":"Duolingo"}'
npx @reneturcios/appworth estimate_app '{"app":"570060128"}' npx @reneturcios/appworth search_apps '{"query":"Duolingo"}' npx @reneturcios/appworth --version
Output is the tool's result text (the upstream body on success). Exit codes: 0 on success, 1 on a runtime error, 2 on a usage error.
npx -y @reneturcios/appworth mcp
MCP client config (the key is optional; provide it through the client's environment when you have one):
{
"mcpServers": { "appworth": { "command": "npx", "args": ["-y", "@reneturcios/appworth", "mcp"], "env": { "APPDEX_API_KEY": " " } } } }
docker run -i ghcr.io/cloudcorprecords/appworth
docker run --rm ghcr.io/cloudcorprecords/appworth search_apps '{"query":"Duolingo"}'
npm install
npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (fake fetch only, no network) npm run dev # run the CLI from source
MIT — Copyright (c) 2026 Rene Turcios