storeshots-mcp

storeshots-mcp

Ship App Store and Google Play screenshots without opening a design tool.

storeshots-mcp turns raw app screenshots into finished store-listing visuals — device frames, benefit-driven headlines, brand backgrounds, and exact store dimensions for iOS and Android. It runs as an MCP server, so the AI agent you already use writes and translates the copy while storeshots renders the pixels. No design tool, no subscription, no API keys.

_{Real screens from two shipped apps: bombo (panels 1–3) and Studio Zero (panel 4). Panel 3 is the Android preset with Turkish headlines, uppercased with locale-correct İ and Ğ.}

The idea

Store screenshots are two jobs pretending to be one. There's a creative job (what to say, which screen sells which feature, how to phrase it in six languages) and a production job (frames, typography, exact pixel dimensions, no alpha channel). Design tools make you do both by hand; screenshot SaaS locks the production job behind a subscription.

storeshots-mcp splits them and gives each to whatever is best at it:

Your AI agent decides	storeshots renders
Which screens to feature	Device frames at exact scale
The headline for each one	Typography, contrast, and layout
Idiomatic translations	Correct casing per language (Turkish İ, German ß)
Brand color and order	Deterministic PNGs at exact store dimensions

Because the render path is pure and local, the same inputs always produce the same pixels — no model in the loop, nothing uploaded anywhere.

Install

Claude Code

claude mcp add storeshots -- npx -y storeshots-mcp

Cursor / Windsurf / Claude Desktop / Antigravity / VS Code — add to your MCP config:

{
  "mcpServers": {
    "storeshots": { "command": "npx", "args": ["-y", "storeshots-mcp"] }
  }
}

Codex CLI — add to ~/.codex/config.toml:

[mcp_servers.storeshots]
command = "npx"
args = ["-y", "storeshots-mcp"]

It's a plain stdio MCP server with zero client-specific behavior, so it works in any MCP-capable agent. No server at all? The same engine is a CLI: npx storeshots --help.

Use it

Point your agent at your raw screenshots and describe the set you want:

"Take the screenshots in ./raw-shots and generate a full App Store and Play Store set. Brand color #E31837, 6 screenshots, English and Turkish."

The agent reads the screens, writes the headlines, and calls generate_set once per platform and language. You get back finished PNGs, already the right size, ready to upload. Ask for changes in plain language and it re-renders only what moved.

What it produces

5 presets, each at the exact size its store requires:

Preset	Store	Dimensions
ios-phone	App Store, iPhone 6.9"	1320 × 2868
android-phone	Google Play, phone	1080 × 1920
ipad-13	App Store, iPad Pro 13"	2064 × 2752
android-tablet	Google Play, 10" tablet	1600 × 2560
play-feature-graphic	Google Play feature graphic	1024 × 500

And the finishing touches that make a set look designed:

• Built-in device frames — iPhone (dynamic island), Pixel-style Android (punch hole), iPad, and tablet, drawn programmatically at exact scale. Bring your own with custom frames.
• Layout variants — text-top, text-bottom, and tilted; mix them across a set so it doesn't look like one template copied six times.
• Panoramic sets — one gradient flowing continuously across every panel, so the row reads as a single image in the store. See panoramas.
• Benefit-first headlines — a bold verb plus a short descriptor, auto-uppercased with locale-correct special characters and contrast-aware color.
• Showcase composer — one wide preview image of the whole set for your repo, launch post, or client deck.

Every output is flattened to remove the alpha channel that App Store Connect rejects, and validated against its preset before it's written.

Tools

Tool	What it does
list_presets	List every preset with its store and exact dimensions
compose_screenshot	Render one screenshot (background, frame, headline, source image)
generate_set	Batch-render an ordered set for one platform + language; supports panoramas
create_showcase	Stitch generated screenshots into one preview strip
validate_screenshot	Check an image against store dimension and format rules

Each tool returns file paths plus a structured summary, so the agent can review and iterate.

Multi-language sets

Translation lives in the agent, not the server. Generate English once, then:

"Now do the same set in Turkish and German."

The agent translates each headline idiomatically; storeshots renders it with correct locale casing. Files follow a predictable convention:

output/
  en/ios-phone/en_01.png … en_06.png
  tr/ios-phone/tr_01.png … tr_06.png
  de/android-phone/de_01.png … de_06.png

Panoramic sets

Pass panorama to generate_set and the per-panel solid background becomes one horizontal gradient sliced across the whole set — so placed side by side in the store, the screenshots form a single continuous image.

// generate_set arguments
{
  "preset": "ios-phone",
  "background": "#27AF99",           // gradient start
  "panorama": { "to": "#1E3A8A" },   // gradient end, flowing across all panels
  "outputDir": "output/en/ios-phone",
  "items": [ /* one entry per screenshot */ ]
}

Custom frames

Prefer a specific device look? Supply your own frame PNG (transparent where the screen shows through) and the pixel rectangle the screenshot fills:

{
  "frame": {
    "image": "./frames/iphone-16-pro.png",
    "screenX": 40, "screenY": 40,
    "screenWidth": 1080, "screenHeight": 2280
  }
}

Works on compose_screenshot and as a set-wide option on generate_set; omit it to use the built-in frames.

Claude Code skill (optional)

The tools work on their own, but the bundled skill adds a guided workflow — benefit discovery from your codebase, headline approval before rendering, per-language sets, and upload guidance:

mkdir -p ~/.claude/skills/storeshots
curl -o ~/.claude/skills/storeshots/SKILL.md \
  https://raw.githubusercontent.com/mtbun/storeshots-mcp/main/skill/SKILL.md

Then ask Claude Code for "store screenshots for this app" and it walks the whole flow.

Design principles

• Deterministic — no AI image generation in the render path; same input, same pixels.
• Zero config — no API keys, no accounts, fully offline.
• Store-correct by construction — dimensions are enforced and validated, not suggested.
• Agent-native — tools expose structured data; the copywriting stays in the model where it belongs.

Roadmap

• Claude Code skill with a guided benefit-discovery workflow
• Play Store feature graphic preset (1024 × 500)
• Layout variants — text-top, text-bottom, tilted
• Custom device frames
• Panoramic sets
• App preview video frames
• More stores (Mac App Store, Chrome Web Store)

Contributing

Issues and PRs welcome. AGENTS.md documents the architecture and conventions, for human contributors and coding agents alike.

License

MIT