Storelift

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.