openaso
App Store Optimization for AI agents: keyword ranks, suggestions, popularity, competitors, reviews
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http openaso 'https://mcp.openaso.ai/mcp' --header 'Authorization: <Bearer auth with an openaso API key — create one free at https://openaso.ai>'
{
"mcpServers": {
"openaso": {
"type": "http",
"url": "https://mcp.openaso.ai/mcp",
"headers": {
"Authorization": "<Bearer auth with an openaso API key — create one free at https://openaso.ai>"
}
}
}
}
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
openaso — App Store Optimization for AI agents
openaso is a hosted MCP server that gives AI agents real App Store Optimization data from Apple's public app-store APIs: keyword ranks, search-autocomplete suggestions, keyword popularity (real Apple Search Ads popularity where available), competitor intelligence, review mining, chart positions, local metadata keyword-coverage analysis, and account-scoped daily rank tracking.
- Website / signup: https://openaso.ai
- Endpoint:
https://mcp.openaso.ai/mcp(Streamable HTTP, stateless) - Official MCP registry:
ai.openaso/openaso - Docs: https://openaso.ai/docs · tool contracts: https://openaso.ai/tools
- Agent-readable docs: https://openaso.ai/llms.txt and https://openaso.ai/llms-full.txt
(every docs page is also served as markdown at its URL +
.md)
This repository is the public home of openaso: connection docs, examples, and the issue tracker. The server's source code is proprietary and is not published here.
Quick start
- Create a free account and mint an API key at https://openaso.ai (free tier: 500 tool calls/day, 500 tracked app × keyword × storefront combinations).
- Connect your client.
Claude Code
claude mcp add openaso --transport http https://mcp.openaso.ai/mcp \
--header "Authorization: Bearer YOUR_KEY"
Any MCP client (JSON config)
{
"mcpServers": {
"openaso": {
"url": "https://mcp.openaso.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_KEY" }
}
}
}
Authentication is Authorization: Bearer <key> (an x-api-key header also works).
Tools
Everything is per-storefront: ranks, availability, suggestions and popularity differ by country,
so tools take an explicit countries list (default ["US"]).
| Tool | What it returns |
|---|---|
rank | An app's position in App Store search results for a keyword (top 200), per storefront. |
suggest | App Store search-autocomplete suggestions for a seed term — the terms Apple itself suggests. |
volume | Keyword demand (popularity 0–100, Apple Search Ads popularity where available) plus competition count. |
competitors | Top-ranking apps for a keyword: position, ratings, genre, keyword-in-title. |
app | Metadata for one app per storefront, including whether it is available there. |
audit | One-call ASO research bundle: current listing, indexed word pool, autocomplete-discovered keyword candidates scored for demand and competition. |
coverage | Which search phrases a metadata draft can rank for — computed locally from the title/subtitle/keyword-field word pool, no network. |
reviews | Recent customer reviews from Apple's public RSS: rating distribution, average, texts. |
charts | Position on the top-free, top-paid and top-grossing charts (top 100), per storefront. |
revenue | Order-of-magnitude revenue estimate modeled from public top-grossing chart rank. |
track_config | Manage the account's tracked set of (app × keyword × storefront) combinations. |
track | Snapshot ranks for everything in the tracked set, on demand. |
history | Server-side rank history — written by track and by the managed daily tracking run. |
Why agents like it
Apple indexes an app's title (30 chars), subtitle (30) and hidden keyword field (100) as one
combined word pool — an app can rank for any query assembled from words across those fields.
openaso's tools are built around that model: audit finds the candidates, coverage scores a
draft's pool locally, rank/volume verify against the real store. The full model is explained
in the docs (agents: llms.txt).
Support
- Bugs and feature requests: issues
- Email: <hector@instasize.com>
Legal
© 2026 Hector Lopez. All rights reserved. openaso is not affiliated with, endorsed by, or sponsored by Apple Inc. App Store® and iTunes® are trademarks of Apple Inc. Data is retrieved from Apple's public endpoints; you are responsible for using it in compliance with Apple's terms.
Frequently asked questions
What is openaso?
App Store Optimization for AI agents: keyword ranks, suggestions, popularity, competitors, reviews
How do I install openaso?
It runs as a remote server. In Claude Code: claude mcp add --transport http openaso 'https://mcp.openaso.ai/mcp' --header 'Authorization: <Bearer auth with an openaso API key — create one free at https://openaso.ai>'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does openaso need an API key?
Yes. It expects Authorization, which you set in its configuration.
Is openaso open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains openaso?
It is published by xekor. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.