aso-mcp 0.1.1

AI-first App Store keyword research — plug into Claude, Cursor, or any MCP client. No API keys needed.

🔍 aso-mcp

Free App Store keyword research for your AI. No API keys. No signup. No subscription.

Plug it into Claude, Cursor, Windsurf, or any MCP client and research App Store keywords conversationally.

---

Install in 10 seconds

Claude Code

claude mcp add aso -- uvx aso-mcp

Claude Desktop

Add to your config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "aso": {
      "command": "uvx",
      "args": ["aso-mcp"]
    }
  }
}

Cursor / Windsurf

Add to your MCP settings:

{
  "mcpServers": {
    "aso": {
      "command": "uvx",
      "args": ["aso-mcp"]
    }
  }
}

That's it. No API keys. No environment variables. Just works.

---

What can it do?

Once installed, just talk to your AI naturally:

"Research the keyword 'habit tracker' in the US App Store"

"Compare these keywords and rank them by opportunity: cable identifier, wire color code, voltage calculator, circuit breaker finder"

"Find me keywords with popularity above 30 and difficulty below 40 from this list: ..."

"Show me who's ranking for 'meditation app' and how hard it is to compete"

"Suggest optimized metadata for my app CableID targeting cable identification keywords"

"Scan 'budget planner' across the US, UK, Germany, Japan and Brazil stores"

---

Tools

Tool	What it does
aso_research_keyword	Full analysis — popularity, difficulty, opportunity score, download estimates, top competitors
aso_batch_research	Research up to 20 keywords at once, ranked by opportunity
aso_competitor_analysis	Deep dive into who's ranking — ratings, reviews, pricing, developer, app age
aso_find_opportunities	Scan up to 30 keywords, filter by your thresholds, return only the good ones
aso_suggest_metadata	Generate optimized title, subtitle, and keyword field backed by real data
aso_country_scan	Check a keyword across up to 15 App Store regions

---

How scoring works

All data comes from Apple's free iTunes Search API. No paid APIs, no scraping, no Apple Search Ads account needed.

Popularity (1–100)

A 6-signal model estimating how often a keyword is searched:

Signal	Points	What it measures
Result count	0–25	How many apps appear for this keyword
Leader strength	0–30	Rating volume of top-ranking apps
Title match density	0–20	How many apps use this keyword in their title
Market depth	0–10	Whether strong apps appear deep in results
Specificity penalty	−30 to 0	Adjusts for generic terms that inflate counts
Exact phrase bonus	0–15	Rewards multi-word keywords with precise matches

Difficulty (1–100)

A 7-factor weighted model estimating how hard it is to rank:

Factor	Weight	What it measures
Rating volume	30%	How many ratings competitors have
Dominant players	20%	Whether apps with 100K+ ratings dominate
Rating quality	10%	Average star ratings
Market maturity	10%	How long competitors have been listed
Publisher diversity	10%	Few publishers vs many
App count	10%	Total number of results
Content relevance	10%	How well results actually match the keyword

Opportunity labels

Label	Meaning
Sweet Spot	High popularity + low difficulty — go build this
Hidden Gem	Decent popularity + very low difficulty
Competitive Opportunity	High popularity, moderate difficulty — needs a strong USP
Worth Investigating	Promising but do more research
Low Volume	Easy to rank but few people searching
Avoid	Too competitive for the search volume

Download estimates

3-stage pipeline per ranking position: popularity → estimated daily searches → tap-through rate (power-law decay) → install conversion (35–55% for free apps).

---

Rate limits

The iTunes Search API is free but rate-limited. The client enforces a 3-second minimum between requests. Batch operations take roughly n × 3 seconds.

---

FAQ

How accurate is this compared to paid tools like Astro or AppTweak?

Paid tools have access to Apple Search Ads impression data across thousands of advertisers, giving them more precise volume estimates. This tool uses publicly available iTunes Search API data with a multi-signal scoring model. It's very good for relative comparisons (keyword A vs keyword B) and identifying opportunities. It won't give you the exact daily search volume that a $100/month tool would.

Do I need an Apple developer account?

No. The iTunes Search API is completely public.

Does this work for Google Play?

Not yet. The iTunes Search API only covers the Apple App Store. Google Play support would require a different data source.

Can I use this for commercial research?

Yes. MIT licensed. Do whatever you want with it.

---

Contributing

PRs welcome. If you want to improve the scoring model, add new tools, or support new data sources, open an issue first so we can discuss the approach.

---

License

MIT — free to use, modify, and distribute.

---

Built by @heyb3n_ — electrician turned iOS dev, building AI tools for indie developers.