About ASO Atlas
ASO Atlas is an ASO platform for App Store and Google Play developers to research keywords, track rankings, and review app performance. Its MCP server can read account data and manage research settings without changing store listings.
Key features
- 01Keyword popularity and difficulty research
- 02Daily rank tracking across 59 storefronts
- 03Competitor keyword gap analysis
- 04Metadata optimization and draft saving
- 05App Store Connect performance analysis
Use cases
- 01Compare search potential across keywords
- 02Track app rankings across storefronts
- 03Find keywords competitors rank for but the app lacks
- 04Review store metadata and performance
MCP support
The hosted MCP server exposes tools to query and manage an ASO Atlas account. It supports OAuth 2.1 or personal access tokens; write operations affect the ASO Atlas account, not App Store listings.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://asoatlas.com/mcpclaude mcp add --transport http com-asoatlas https://asoatlas.com/mcp{"mcpServers":{"com-asoatlas":{"type":"http","url":"https://asoatlas.com/mcp"}}}Open in Cursor{"servers":{"com-asoatlas":{"type":"http","url":"https://asoatlas.com/mcp"}}}Open in VS Code{"mcpServers":{"com-asoatlas":{"type":"http","url":"https://asoatlas.com/mcp"}}}{"mcpServers":{"com-asoatlas":{"serverUrl":"https://asoatlas.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project README![]()
ASO Atlas MCP server
ASO Atlas is an App Store Optimization tool for App Store and Google Play apps: keyword research with Apple-reported search popularity and a difficulty score, daily rank tracking in 59 storefronts, competitor keyword gaps, a metadata optimizer and your own App Store Connect performance.
This repository holds the public manifests for its hosted MCP server, so any MCP client can research keywords and act on your ASO Atlas account mid-conversation.
- Server URL:
https://asoatlas.com/mcp(Streamable HTTP) - Auth: OAuth 2.1 with PKCE and dynamic client registration, or a personal access token for headless agents
- Docs: https://asoatlas.com/docs/connect-your-ai
- Requires: an ASO Atlas account with an active subscription ($9/month, unlimited apps and keywords)
Install
Claude
Claude.ai (web or desktop): Settings → Connectors → Add custom connector → paste the server URL and approve the consent screen.
Claude Code:
claude mcp add --transport http asoatlas https://asoatlas.com/mcp
Or install this repository as a plugin, which adds the server together with a skill that teaches Claude how to read popularity and difficulty:
claude plugin marketplace add asoatlas/mcp
claude plugin install aso-atlas@asoatlas-mcp
Cursor
Add to Cursor, or in ~/.cursor/mcp.json:
{ "mcpServers": { "asoatlas": { "url": "https://asoatlas.com/mcp" } } }
VS Code
code --add-mcp '{"name":"asoatlas","type":"http","url":"https://asoatlas.com/mcp"}'
Gemini CLI
gemini extensions install https://github.com/asoatlas/mcp
The extension adds the server and the same skill. Sign in with /mcp auth asoatlas.
Google Antigravity
In mcp_config.json (Agent panel → MCP Servers → Manage → View raw config):
{ "mcpServers": { "asoatlas": { "serverUrl": "https://asoatlas.com/mcp" } } }
Or install this repository as an Antigravity plugin, which adds the server together with the skill:
agy plugin install https://github.com/asoatlas/mcp
Kiro
Add to Kiro, or in .kiro/settings/mcp.json:
{ "mcpServers": { "asoatlas": { "url": "https://asoatlas.com/mcp" } } }
Windsurf
In ~/.codeium/windsurf/mcp_config.json:
{ "mcpServers": { "asoatlas": { "serverUrl": "https://asoatlas.com/mcp" } } }
Cline, Kilo Code and Roo Code
MCP Servers → Remote Servers → name asoatlas, URL https://asoatlas.com/mcp, transport Streamable HTTP.
Goose
goose configure → Add Extension → Remote Extension (Streamable HTTP) → https://asoatlas.com/mcp.
LM Studio
Codex
Install this repository as a plugin, which adds the server together with the same skill:
codex plugin marketplace add asoatlas/mcp
codex plugin add aso-atlas@asoatlas
codex mcp login asoatlas
Or only the server, in ~/.codex/config.toml:
[mcp_servers.asoatlas]
url = "https://asoatlas.com/mcp"
then codex mcp login asoatlas to approve the consent screen.
ChatGPT
Settings → Security and login → turn on Developer mode, then Plugins → + → paste the server URL. The OAuth prompt signs you in to ASO Atlas.
Hermes Agent, containers and other headless clients
The OAuth callback cannot reach a client that runs on a server, so create a personal access token under Settings → Connect your AI on asoatlas.com and send it as a header:
mcp_servers:
asoatlas:
url: https://asoatlas.com/mcp
headers:
Authorization: Bearer YOUR_TOKEN
Any other client that speaks MCP over HTTP works the same way: give it the URL, then either complete the OAuth prompt or configure the bearer header.
Tools
Everything is scoped to the signed-in user's own account. Read tools never change anything; write tools change the ASO Atlas account only, never the App Store listing itself.
| Tool | Kind | What it does |
|---|---|---|
list_tracked_apps | read | The apps you track, with the ids the other tools take |
get_dashboard | read | Per-app top 10 / top 50 counts, visibility trend, biggest moves |
get_app | read | One app in depth: keywords with rank, popularity, difficulty; competitors; keyword gap |
get_app_optimizer | read | Metadata analysis for one storefront: coverage, missing terms, character budgets |
get_app_performance | read | App Store Connect digest: funnel, monetization, health, territories |
get_performance_series | read | Daily history of one App Store Connect metric, optionally split by dimension |
research_keywords | read | Popularity, difficulty and result count for up to 50 terms in a storefront |
app_ranking_keywords | read | Reverse lookup: what any App Store app ranks for |
keyword_suggestions | read | Autocomplete ideas for a seed term |
list_keyword_lists / get_keyword_list | read | Saved research collections |
track_app / untrack_app | write | Start or stop tracking an app |
add_keywords / remove_keyword | write | Track or drop keywords per storefront |
add_competitor / remove_competitor | write | Manage the competitors behind the keyword gap |
change_app_market | write | Move an app to another storefront |
refresh_app | write | Queue a fresh rank, rating and review check |
save_metadata_draft | write | Save a title / subtitle / keyword-field draft for the optimizer |
create_keyword_list / add_keyword_to_list / remove_keyword_from_list | write | Manage keyword lists |
Every tool carries readOnlyHint, destructiveHint and openWorldHint annotations; destructive tools delete ranking history and say so in their description.
What is in this repository
server.json: the entry published to the official MCP Registry ascom.asoatlas/mcp.claude-plugin/plugin.json+.claude-plugin/marketplace.json+.mcp.json+skills/aso-atlas/SKILL.md: a Claude Code plugin bundling the server with a skillplugin.json+mcp.json: the same as an Agent Plugin for Codex (OpenAI settings underextensions.com.openai), Cursor and compatible clients;.agents/plugins/marketplace.jsonmakes the repository a Codex marketplacegemini-extension.json: a Gemini CLI extension (server + the skill).antigravity-plugin/plugin.json+mcp_config.json: an Antigravity plugin (server + the skill);plugins/aso-atlas/holds the same without the skillSETUP.md: the connection walkthrough a client can follow after install
The server itself is part of the ASO Atlas web application and is not open source. The manifests and skill here are MIT licensed.
Privacy Policy
The server only ever reads and writes the signed-in user's own ASO Atlas data. Privacy policy: https://asoatlas.com/privacy. Terms: https://asoatlas.com/terms. Support: [email protected].
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.