Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Review classifiers & lead data for Google Maps, Naver and AliExpress — via Apify MCP
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.
AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http leoworks-data-tools 'https://mcp.apify.com/?tools=leoworks/naver-shopping-rank-tracker,leoworks/naver-blog-brand-monitor,leoworks/naver-ai-briefing-monitor,leoworks/korean-review-classifier,leoworks/kbeauty-ranking-review-monitor,leoworks/aliexpress-reviews-classifier,leoworks/aliexpress-search-scraper,leoworks/social-…' --header 'Authorization: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"leoworks-data-tools": {
"url": "https://mcp.apify.com/?tools=leoworks/naver-shopping-rank-tracker,leoworks/naver-blog-brand-monitor,leoworks/naver-ai-briefing-monitor,leoworks/korean-review-classifier,leoworks/kbeauty-ranking-review-monitor,leoworks/aliexpress-reviews-classifier,leoworks/aliexpress-search-scraper,leoworks/social-…",
"headers": {
"Authorization": "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": {
"leoworks-data-tools": {
"type": "http",
"url": "https://mcp.apify.com/?tools=leoworks/naver-shopping-rank-tracker,leoworks/naver-blog-brand-monitor,leoworks/naver-ai-briefing-monitor,leoworks/korean-review-classifier,leoworks/kbeauty-ranking-review-monitor,leoworks/aliexpress-reviews-classifier,leoworks/aliexpress-search-scraper,leoworks/social-…",
"headers": {
"Authorization": "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 address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 6, 2026
The registry name was verified with the GitHub account illee, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
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.
You need to fill in: Authorization
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.3.0) reached the registry 19 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, HotCodePush
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.
Manage over-the-air (OTA) updates for React Native, Expo, Capacitor and Cordova apps.
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.
Seventeen Apify actors for Google Maps review analysis, review health checks and lead scoring, Naver Place review analysis, review sentiment and complaint classification (Korean, Japanese, Spanish, Amazon, social comments), Naver Shopping and Naver Blog data, K-beauty rankings, AliExpress reviews and search, and B2B lead data — exposed as tools through the official Apify MCP server (hosted by Apify). This repository holds no server code: it describes a preconfigured server URL, a Claude Code plugin, and one page per tool with example prompts and sample output.
Each call runs on your Apify account and is billed per result at the actor's price; Apify's free monthly credit covers small tests.
/plugin install leoworks-data-tools --marketplace illee/leoworks-data-tools-mcp
On older Claude Code versions, use two steps:
/plugin marketplace add illee/leoworks-data-tools-mcp
/plugin install leoworks-data-tools@leoworks
Then run /mcp, pick leoworks-data-tools and sign in with your Apify account (OAuth).
Server URL (streamable HTTP):
https://mcp.apify.com/?tools=leoworks/naver-shopping-rank-tracker,leoworks/naver-blog-brand-monitor,leoworks/naver-ai-briefing-monitor,leoworks/korean-review-classifier,leoworks/kbeauty-ranking-review-monitor,leoworks/aliexpress-reviews-classifier,leoworks/aliexpress-search-scraper,leoworks/social-comment-classifier,leoworks/japanese-review-classifier,leoworks/spanish-review-classifier,leoworks/google-maps-review-classifier,leoworks/google-maps-lead-qualifier,leoworks/amazon-review-classifier,leoworks/job-posting-classifier,leoworks/company-website-classifier,leoworks/naver-place-review-classifier,leoworks/google-maps-review-health-check
Auth: Authorization: Bearer (Apify Console → Settings → API & Integrations), or leave the header out to sign in with OAuth. Keep only the tools you need in ?tools=.
Claude Code, without the plugin
claude mcp add --transport http leoworks "<server URL>" --header "Authorization: Bearer YOUR_APIFY_TOKEN"
Claude Desktop / Cursor (mcp.json)
{ "mcpServers": { "leoworks": { "url": "<server URL>", "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" } } } }
Google Maps
Review & comment classifiers
Korea: Naver & K-beauty
AliExpress
B2B lead data
More prompts, an input example and sample output for every tool are in tools/.
Call any tool without an AI agent: examples/ has a folder for each of the first fifteen tools with a ready-to-run input.json, Python (apify-client), JavaScript (Node 18+) and curl scripts, plus the MCP setup for Claude Code, Cursor and Claude Desktop. Put your Apify token in the APIFY_TOKEN environment variable — the files never contain a token.
export APIFY_TOKEN="<your token>"
python examples/korean-review-classifier/example.py
| Tool | What it does | Price | Code |
|---|---|---|---|
leoworks--google-maps-review-classifier | Classify Google Maps reviews from any Google Maps reviews scraper's dataset: complaint types, what customers praise, serious issues (safety, discrimination, fraud), sentiment and unanswered reviews — plus a reply queue and per-place CSV. No LLM key. | $0.50 / 1,000 reviews (+ compass' Google Maps scraper, billed separately, when the tool collects the reviews — see the cost note) | examples |
leoworks--google-maps-review-health-check | Free review health check for one Google Maps business: average stars, owner reply rate, 1–3 star reviews with no owner reply, and the last 90 days versus before. It only counts — no AI, no login. | Free (+ compass' Google Maps scraper, billed separately: about $0.02 for 30 reviews) | — |
leoworks--google-maps-lead-qualifier | Score Google Maps places from any Google Maps scraper against your ideal customer in plain language: lead score, tier A–D, a reason per lead, chain check, emails and socials kept, LEADS.csv. Free filters. No LLM key. | $2 / 1,000 places (+ compass' Google Maps scraper, billed separately, when the tool collects the places — see the cost note) | examples |
| Tool | What it does | Price | Code |
|---|---|---|---|
leoworks--korean-review-classifier | Classify Korean customer reviews — Coupang reviews (쿠팡 리뷰), Olive Young reviews, Naver Shopping and Naver Place reviews — into complaint types, sentiment and purchase motive with probabilities. Korean review sentiment analysis for any review scraper's dataset — no scraping, no prompt writing. | $0.50 / 1,000 reviews | examples |
leoworks--amazon-review-classifier | Classify Amazon reviews from any Amazon reviews scraper: complaint and return reasons, what buyers praise, sentiment, star-vs-text mismatch and worst variants — plus an action queue and per-product CSV. No LLM key. | $0.50 / 1,000 reviews | examples |
leoworks--japanese-review-classifier | Classify Japanese customer reviews — Rakuten (楽天レビュー), Amazon.co.jp and any review scraper's dataset — into complaint types, sentiment and purchase motive with probabilities. Japanese review sentiment analysis (レビュー分析), no prompts, no LLM key. | $0.50 / 1,000 reviews | examples |
leoworks--spanish-review-classifier | Classify Spanish customer reviews — MercadoLibre (reseñas y opiniones), AliExpress and any review scraper's dataset — into complaint types, sentiment and purchase motive with probabilities. Spanish review sentiment analysis (análisis de reseñas), no prompts, no LLM key. Beta. | $0.50 / 1,000 reviews (beta) | examples |
leoworks--social-comment-classifier | Classify Instagram, TikTok, Facebook and YouTube comments from any comment scraper's dataset: purchase intent, questions, complaints, requests, praise, spam and sentiment, with probabilities. Comment sentiment analysis, no prompts, no LLM key. | $0.50 / 1,000 comments | examples |
| Tool | What it does | Price | Code |
|---|---|---|---|
leoworks--naver-shopping-rank-tracker | Track where your products, URLs or Smartstore stores rank in Naver Shopping search for any Korean keyword (네이버 쇼핑 순위, 스마트스토어 순위). Organic rank 1–35 plus ad slot position, price, reviews and rating — a Naver Shopping scraper built for scheduled rank monitoring. | $3 / 1,000 keyword checks (+$0.50 / 1,000 competitor rows) | examples |
leoworks--naver-blog-brand-monitor | Monitor a brand or product on Naver Blog (네이버 블로그), Korea's biggest review platform. This Naver Blog scraper collects posts by keyword and labels each one sponsored (체험단/협찬) or self-paid with evidence, plus sentiment and brand mentions — Korean social listening in one run. | $4 / 1,000 posts + $1 / 1,000 judgments | examples |
leoworks--naver-ai-briefing-monitor | Track your brand in Naver's AI briefing (네이버 AI 브리핑), the generative answer atop Korea's #1 search engine — Google AI Overviews for Korea. Capture the answer, cited sources, AI ads and related questions, and see if your brand or rivals are mentioned and recommended (GEO). | $3 / 1,000 queries + $12 / 1,000 briefings captured | examples |
leoworks--naver-place-review-classifier | Analyze Naver Place reviews (네이버 플레이스 리뷰) of restaurants and cafés: 9 complaint types, sentiment, serious issues and reviews that still have no owner reply, as a reply queue — plus optional sponsored-or-not labels for blog posts about the place. No prompts, no LLM key. | $0.50 / 1,000 reviews judged (+ a separate Naver Place scraper, billed separately, about $1 / 1,000 reviews, when the tool collects the reviews) | — |
leoworks--kbeauty-ranking-review-monitor | Track K-beauty bestseller rankings on Olive Young Global (OliveYoung, 올리브영) and Amorepacific's Amore Mall (아모레몰: Sulwhasoo, Laneige, Hera…) and collect Korean cosmetics reviews with optional AI classification — complaint types, sentiment and purchase motive in Korean, English and Japanese. | $2 / 1,000 ranking rows · $1 / 1,000 reviews · $0.50 / 1,000 classifications | examples |
| Tool | What it does | Price | Code |
|---|---|---|---|
leoworks--aliexpress-reviews-classifier | Scrape AliExpress product reviews — text, English translation, star rating, date, buyer country, option (SKU) and photos — from any product URL. Optional AI classification adds complaint types, sentiment and purchase motive, plus a per-product summary. No login. | $1.50 / 1,000 reviews + $0.50 / 1,000 classifications | examples |
Only the beginning is shown; read the rest in the repo