# storelift [Health: Active]

**Category:** 🎯 Marketing  
**Repository:** https://github.com/vom-core/storelift-mcp  
**GitHub Stars:** 1  
**npm Downloads (last month):** 395  
**Views:** 4  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/storelift

## Description
App Store & Google Play keyword ranks, rivals and AI visibility as an MCP server

## Tools
Capabilities this server exposes over MCP:

- **list_apps** — List the apps tracked in this Storelift account (id, name, countries, keywords). Call this first — every other tool needs an appId from here.
- **get_keywords** — Keyword ranks for one app in one App Store / Google Play country. THREE STATES ARE DISTINCT: measured=false means the query could not be measured, rank=null means it was measured but the app is absent from the top results, rank=<number> is the rank. Never collapse them into one — counting an unmeasured day as zero produces a false answer.
- **get_rivals** — Apps that rank ABOVE this app in search. For each rival you get the keywords it beats you on, its rank there (theirRank) and yours (ourRank) — ourRank null means the app does not appear for that keyword at all.
- **get_ai_visibility** — Whether AI assistants name this app when asked natural questions about its category — reported per engine (Claude / ChatGPT / Gemini), never averaged. This is an OBSERVATION, not a ranking: a model's knowledge is frozen at a date and the answer is not identical every time, so read the trend rather than a single measurement.
- **get_history** — Keyword rank history for one country. Series points are [day, rank]; a null rank means the app was absent from the top results that day, which is not the same as a bad rank.
- **get_store_page** — The app's own store listing signals for one country: name, subtitle, version, in-app events, editorial placements, similar-apps shelves and the screenshot set (iOS), plus the Google Play page (exact install count, rating histogram, ad/IAP flags, chart badge). `timeline` lists the dated changes we detected on the listing — the cheapest explanation for a rank move. measured=false means the page was never read; it is not the same as an empty page.
- **get_reviews** — Recent reviews for one country: `list` is the App Store feed, `android` the Google Play page (a narrower window, and Play publishes no review title or version). `newCount` is how many arrived since the previous measurement — null means an older record where the field was never written, which is not zero. android=null means Play was never measured; an empty list means there genuinely are no reviews.
- **get_charts** — App Store chart position for one country: current ranks per list (free / paid / grossing, overall and in category) plus their history. Google Play is absent on purpose — Google publishes no chart list, so there is nothing to read, and a number here would be invented.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "storelift": {
    "command": "npx",
    "args": ["-y","storelift-mcp"],
    "env": {
      "STORELIFT_API_KEY": "",
      "STORELIFT_API": ""
    }
  }
}
```

**Requires environment variables:** `STORELIFT_API_KEY`, `STORELIFT_API` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What storelift MCP server does

The storelift MCP server connects an MCP-compatible client to Storelift’s measurements for tracked mobile apps. It covers App Store and Google Play keyword performance, rival apps, reviews, charts, listing signals, and visibility in AI assistants. Storelift measures this data nightly, while the server makes the available results queryable through tools rather than requiring a dashboard.

No App Store or Google Play credentials are needed because ranking data is read from public storefronts. Running tool calls does require a Storelift Pro or Studio plan, because the Public API is enabled on those plans, and an API key generated in Storelift settings.

## How it works

The local package is a dependency-free Node program that communicates over JSON-RPC on stdio. It can be started through `npx -y storelift-mcp` or directly with `node index.mjs`. The `STORELIFT_API_KEY` variable authenticates tool calls, while `STORELIFT_API` can replace the default API base URL of `https://storelift.net`.

A hosted option is available at `https://storelift.net/mcp` over Streamable HTTP. Clients with MCP authorization can use Storelift OAuth; clients without OAuth can send the API key in an Authorization bearer header. Without an API key, the local server still starts and advertises its tools, but calls return an error explaining how to obtain one.

The storelift MCP server also exposes five prompt templates through `prompts/list`. They cover lost keyword positions, the leading app’s listing fields, crash-related reviews, category charts, and AI visibility. The AI visibility prompt requires Studio-plan data.

## Setup and configuration

For a local setup, add the server to an MCP client with the `STORELIFT_API_KEY` environment variable. Claude Code can use its `claude mcp add` command, while Claude Desktop can define the server under `mcpServers` in `claude_desktop_config.json`.

For hosted access, configure the Streamable HTTP URL. OAuth-capable clients can authenticate through Storelift instead of pasting a key. Other clients can include `Authorization: Bearer <key>` with the HTTP connection.

Supported environment variables:

- `STORELIFT_API_KEY`: required for successful tool calls.
- `STORELIFT_API`: optional API base override; defaults to `https://storelift.net`.

## Tools and capabilities

The available tools include:

- `list_apps`: returns tracked app IDs, names, countries, and keywords.
- `get_keywords`: retrieves keyword ranks for one app in one country.
- `get_rivals`: identifies apps ranking above the selected app and shows both ranks.
- `get_ai_visibility`: reports whether Claude, ChatGPT, and Gemini mention the app.
- `get_history`: returns rank history as day-and-rank points.
- `get_store_page`: combines listing signals, the Google Play page, and a dated change timeline.
- `get_reviews`: returns recent App Store and Google Play reviews plus the count added since the previous measurement.
- `get_charts`: returns App Store chart positions by list with history.

## Limitations and notes

Keyword results distinguish three conditions: an unmeasured query, a measured keyword absent from the top results, and a measured numeric rank. Treating the first condition as rank zero can distort a chart. Google Play is not included in chart results because Google does not publish a chart list.

AI visibility is an observation rather than a fixed ranking. Model knowledge is date-bound, and repeated answers may differ, so trends are more useful than one measurement. A rank change may also relate to a release, reviews, or a chart movement; the listing, review, and chart tools provide context for investigating those changes.

The storelift MCP server is licensed under MIT.

_Full upstream README: https://allmcps.com/mcp/storelift/readme_