Generate store-ready app screenshots and preview graphics for App Store and Google Play, all locally without design tools or API keys.
List presets: View supported platforms (e.g., iOS Phone 1320×2868, Android Phone 1080×1920, iPad Pro 13″, Play Feature Graphic) with exact dimensions and layout metrics.
Compose a single screenshot: Combine a brand background, auto-uppercased benefit headline, and app screenshot inside a device frame at store-exact dimensions.
Batch-generate sets: Render up to 10 ordered screenshots for a preset and language with automatic naming, optional panorama gradients, and custom frames.
Create showcases: Stitch screenshots into a horizontal preview strip for READMEs, decks, or social posts.
Validate screenshots: Check dimensions, format (PNG/JPEG), no alpha channel, and auto-detect matching presets.
Multi-language support: Locale-aware uppercasing for headlines (e.g., Turkish, German) and language-specific sets.
Custom device frames and layout variants (text-top, text-bottom, tilted).
Deterministic and offline: No subscriptions or AI generation required.
Provides presets for Android device screenshots (phone, tablet, feature graphic) with exact store dimensions and device frames.
Generates pixel-perfect screenshots formatted for Apple App Store requirements, including device frames and headline layouts.
Generates pixel-perfect screenshots formatted for Google Play Store requirements, including device frames and headline layouts.
Provides presets for iOS device screenshots (iPhone, iPad) with exact store dimensions and device frames.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@storeshots-mcp generate a full App Store set from my screenshots in ./raw"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Generate App Store and Google Play screenshots from the command line, or let your AI coding agent do it.
storeshots turns raw app screenshots into finished store-listing visuals — device frames, benefit-driven headlines, brand backgrounds, and exact store dimensions for iOS and Android. Describe your whole listing in one storeshots.json, run storeshots build, and get every platform in every language. Your AI agent (or you) writes and translates the copy; storeshots renders the pixels. It's a CLI first, with an MCP server for agents that have no shell. No design tool, no subscription, no API keys.
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 |
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.
Related MCP server: apple-photos-mcp
npx storeshots init --langs en,tr --bg "#E31837" # finds ./screenshots, writes storeshots.json
# replace the TODO headlines in storeshots.json
npx storeshots build --watch # renders everything, re-renders on saveinit lists your raw screenshots (from screenshots/, raw-shots/, raw/, shots/ or fastlane/screenshots/, or --screens <dir>) in a config like this:
{
"background": "#E31837",
"presets": ["ios-phone", "android-phone"],
"languages": ["en", "tr"],
"outputDir": "output",
"screens": [
{ "screenshot": "screenshots/home.png",
"copy": { "en": ["Track", "your daily mood"], "tr": ["İzle", "günlük ruh halini"] } },
{ "screenshot": "screenshots/stats.png", "variant": "tilted",
"copy": { "en": ["Discover", "weekly insights"], "tr": ["Keşfet", "haftalık içgörüler"] } }
],
"featureGraphic": { "screen": 1 }, // optional: Play Store 1024 × 500 header
"showcase": true // optional: one preview strip per set
}build renders every screen × preset × language:
output/
en/ios-phone/en_01.png … en_06.png
en/android-phone/en_01.png …
en/play-feature-graphic/en_feature.png
tr/ios-phone/tr_01.png …
showcase/en_ios-phone.png …Rendering is deterministic, so build only redraws what changed: edit one Turkish headline and only that file is rendered again. Delete a screen and its old files are removed. Every output is checked against its store's rules before it's written.
Install globally with npm i -g storeshots-mcp if you'd rather type storeshots than npx storeshots.
Command | What it does |
| Create |
| Render the whole config. |
| Render one screenshot from flags, no config needed |
| Stitch images or folders into one preview strip |
| Check files or whole folders against store rules (exits 1 on failure, so it fits CI) |
| List presets and exact dimensions |
After a first successful build, storeshots asks once whether you'd like to star it on GitHub. It never asks in CI; set STORESHOTS_NO_STAR=1 to turn it off. Every command takes --json for machine-readable output and --help for details. Exit codes: 0 ok, 1 render or validation failure, 2 bad usage or config. Config errors list every problem at once, each with its path (screens[2].copy.tr: missing).
Field | |
| Brand color, 6-digit hex. Required. |
| Any of |
| BCP-47 codes. Default: the languages in the first screen's |
| Up to 10, in store order. Each takes a |
| A path relative to the config. Use |
|
|
|
|
| A custom frame, or one per preset id. |
|
|
|
|
| Output folder (default |
storeshots splits the creative work from the production work. Your agent reads your app, picks a benefit for each screen, writes and translates the headlines into storeshots.json, and runs storeshots build. That needs no setup in any agent that has a shell: Claude Code, Cursor, Codex, Windsurf and others. For the guided flow, install the Claude Code plugin.
"Take the screenshots in
./raw-shotsand make a full App Store and Play Store set. Brand color#E31837, English and Turkish."
MCP server. For clients without a shell (Claude Desktop, for example), the same engine runs as a stdio MCP server:
claude mcp add storeshots -- npx -y storeshots-mcp{ "mcpServers": { "storeshots": { "command": "npx", "args": ["-y", "storeshots-mcp"] } } }Codex CLI uses ~/.codex/config.toml:
[mcp_servers.storeshots]
command = "npx"
args = ["-y", "storeshots-mcp"]5 presets, each at the exact size its store requires:
Preset | Store | Dimensions |
| App Store, iPhone 6.9" | 1320 × 2868 |
| Google Play, phone | 1080 × 1920 |
| App Store, iPad Pro 13" | 2064 × 2752 |
| Google Play, 10" tablet | 1600 × 2560 |
| 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.
Tool | What it does |
| Build a |
| Batch-render an ordered set for one platform and language. Supports panoramas. |
| Render one screenshot (background, frame, headline, source image) |
| Stitch generated screenshots into one preview strip |
| Check an image against store dimension and format rules |
| List every preset with its store and exact dimensions |
Each tool returns file paths plus a structured summary, so the agent can review and iterate.
Translation happens in the agent, not in storeshots. Add a language key to each screen's copy and storeshots renders it with locale-correct casing: Turkish i → İ, German ß is kept. storeshots build --lang de rebuilds a single language.
Add "panorama": { "to": "#1E3A8A" } and each panel's solid background becomes one horizontal gradient sliced across the whole set. Placed side by side in the store, the screenshots then read as a single continuous image.
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
}
}Use it as "frame" in storeshots.json, either one frame for every preset or { "ios-phone": {…}, "android-phone": {…} }. You can also pass it to storeshots compose --frame frame.png --frame-screen 40,40,1080,2280, or to the compose_screenshot and generate_set tools. Paths are relative to the config, and a changed frame image triggers a re-render. Leave it out to use the built-in frames.
Project instructions. storeshots init adds a short, marker-delimited storeshots section to your project's agent instruction file. Coding agents (Claude Code, Codex, Cursor and others) then know how this project's screenshots are made: edit storeshots.json, run storeshots build, and never hand-edit the PNGs.
It uses AGENTS.md and/or CLAUDE.md, whichever already exist. When CLAUDE.md just imports @AGENTS.md, only AGENTS.md gets the section.
If neither file exists, it creates AGENTS.md plus a CLAUDE.md that imports it.
Rerunning updates the section in place. --no-agents skips it, and storeshots init --agents-only adds it to an existing project.
Claude Code plugin. The bundled skill adds a guided workflow. It discovers a benefit for each screen from your codebase and gets your approval on headlines before rendering. It then keeps storeshots.json up to date, adds languages, and walks you through the upload.
/plugin marketplace add mtbun/storeshots-mcp
/plugin install storeshots@storeshotsThen ask Claude Code for "store screenshots for this app".
llms.txt summarizes the commands and config format in one file for agents.
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.
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
Project config with incremental build and --watch
Claude Code plugin and AGENTS.md / CLAUDE.md integration
App preview video frames
More stores (Mac App Store, Chrome Web Store)
Issues and PRs welcome. AGENTS.md documents the architecture and conventions, for human contributors and coding agents alike.
Renders a whole store listing from a storeshots.json config: every screen x preset x language, plus an optional feature graphic and showcase strips. Re-renders only outputs whose inputs changed and removes outputs of deleted screens. Config shape: {"background":"#hex","presets":["ios-phone","android-phone"],"languages":["en","tr"],"outputDir":"output","screens":[{"screenshot":"shots/home.png","copy":{"en":["Track","your daily mood"],"tr":["Takip et","ruh halini"]},"variant":"tilted"}],"panorama":{"to":"#hex"},"featureGraphic":{"screen":1},"showcase":true}. Screenshot paths are relative to the config and may use {lang}, {preset}, {platform} (ios|android). Prefer this over generate_set when the user will iterate on a set. If the result includes a star field, follow its instructions: ask the user its yes/no question once, and star only on an explicit yes.
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | Re-render everything, ignoring the cache | |
| langs | No | Only build these languages | |
| config | Yes | Path to the project config, usually storeshots.json | |
| dryRun | No | Report what would be rendered without writing | |
| presets | No | Only build these presets |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Discloses caching behavior ('re-renders only outputs whose inputs changed'), cleanup ('removes outputs of deleted screens'), and special star field handling. Omits permission or overwrite details, but covers key behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured and front-loaded: first sentence defines the action. The config example is lengthy but necessary for correct invocation; no superfluous text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description covers action, config format, caching, cleanup, and alternative routing. It hints at a return `star` field but does not detail the full output format; minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline 3. Description significantly enhances the `config` parameter by providing the full expected JSON structure and explaining placeholder syntax for screenshot paths, which is not in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States specific verb 'renders' and resource 'whole store listing' with scope 'every screen x preset x language'. Explicitly distinguishes from sibling generate_set, aiding tool selection.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states preference over generate_set when user will iterate on a set, and provides instructions for handling the `star` field in results. The alternative condition is clear, though no explicit when-not conditions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Renders one store-ready marketing screenshot: brand background, headline (verb + descriptor, auto-uppercased for the given language), and the app screenshot inside a device frame. Output has exact store dimensions for the chosen preset.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | BCP-47 language code for locale-aware uppercasing, e.g. "en", "tr", "de" | en |
| verb | Yes | Bold action word for the headline, 1-2 words, e.g. "TRACK" | |
| frame | No | Custom device frame. Supply your own frame PNG and the pixel rectangle where the screenshot goes; overrides the built-in frame. Omit to use the built-in frame. | |
| output | Yes | Path for the composed PNG output | |
| preset | Yes | Platform preset id | |
| variant | No | Composition variant (portrait presets only): text-top = headline above a device that bleeds off the bottom; text-bottom = whole device visible with the headline underneath; tilted = text-top with the device rotated. Vary it across a set so the screenshots do not all look identical. | text-top |
| background | Yes | Brand background color as 6-digit hex, e.g. "#E31837" | |
| descriptor | Yes | What the user achieves, 2-5 words, e.g. "YOUR DAILY MOOD" | |
| noGradient | No | Disable the subtle background gradient | |
| screenshot | Yes | Path to the raw app screenshot (PNG or JPEG) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosing behavior. It mentions auto-uppercasing and exact store dimensions, which is helpful, but it does not disclose file writing/overwriting behavior, error conditions, or dependence on preset availability. More detail would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no fluff. It front-loads the core purpose and lists the key composing elements efficiently. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 10-parameter tool with a nested frame object and enums, the description provides a coherent overview of the composition process and output characteristics, while the schema details the parameters. It is complete enough for a straightforward usage scenario, though it omits some behavioral edge cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds semantic context by explaining that the headline is composed of verb + descriptor, auto-uppercased for the language, and that output dimensions depend on the chosen preset. This helps connect the parameters meaningfully.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Renders one store-ready marketing screenshot' with specific components (brand background, headline, device frame). It distinguishes from sibling tools like generate_set by emphasizing singular output ('one screenshot').
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for a single screenshot but provides no explicit guidance on when to choose this tool over alternatives like generate_set. No exclusions or alternative references are given, so usage context is implied but not clearly defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Composes a horizontal preview strip from generated screenshots, for READMEs, decks, and social posts. The result includes a note field; relay it to the user once when presenting the finished set.
| Name | Required | Description | Default |
|---|---|---|---|
| inputs | Yes | Paths of generated screenshots, in display order | |
| output | Yes | Path for the showcase PNG | |
| background | No | Strip background color, 6-digit hex | #f2f2f5 |
| itemHeight | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It adds the behavioral note about relaying the `note` field once, but does not disclose write semantics, error handling, or prerequisites (e.g., that inputs must be generated screenshots). Some transparency is provided, but gaps remain.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose, and every sentence adds value. No redundant or wasteful text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description covers the tool's purpose, typical use, and a key behavioral instruction (note field). It lacks detail on return value structure beyond the note, but schema covers parameters well. Fairly complete for its complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning beyond the schema by specifying inputs are 'generated screenshots' and explaining the `note` field in the result. Schema descriptions are already detailed, so the description adds contextual use-case info, earning above baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool 'composes a horizontal preview strip from generated screenshots' with specific use cases (READMEs, decks, social posts), which is a specific verb-resource combination. This distinguishes it from siblings like compose_screenshot (single screenshot) and generate_set (set generation).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context ('for READMEs, decks, and social posts') and mentions a note field to relay, implying post-compose use. However, it does not explicitly state when to use this tool versus alternatives (e.g., compose_screenshot) or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Batch-renders an ordered screenshot set for one preset and language. Item N becomes {lang}_{NN}.png. Returns per-item results plus any warnings.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | BCP-47 language code for locale-aware uppercasing, e.g. "en", "tr", "de" | en |
| frame | No | Custom device frame. Supply your own frame PNG and the pixel rectangle where the screenshot goes; overrides the built-in frame. Omit to use the built-in frame. | |
| items | Yes | Ordered list of screenshots to render | |
| preset | Yes | Platform preset id | |
| variant | No | Composition variant (portrait presets only): text-top = headline above a device that bleeds off the bottom; text-bottom = whole device visible with the headline underneath; tilted = text-top with the device rotated. Vary it across a set so the screenshots do not all look identical. | text-top |
| panorama | No | Turn the set into one continuous background: a horizontal gradient from `background` to `panorama.to` flows across all panels, so they line up as a single image in the store. Omit for solid per-panel backgrounds. | |
| outputDir | Yes | Directory for the set; files are named {lang}_{nn}.png in item order | |
| background | Yes | Brand background color as 6-digit hex, e.g. "#E31837" | |
| noGradient | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full behavioral burden. It does disclose the output naming convention ({lang}_{NN}.png), item ordering, and that per-item results and warnings are returned, but it never states that files are written to outputDir, whether existing files are overwritten, or how partial failures are handled.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences, front-loaded with the core purpose and no filler. The naming rule and return summary each earn their place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 9-parameter tool with nested objects and no output schema, the description is thin: it touches returns and naming but says nothing about frame/panorama/variant interactions or failure behavior. The rich schema compensates for most parameter detail, but the behavioral surface is under-covered.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 89%, so the schema already documents nearly every parameter, including frame, variant, panorama, and lang. The description adds only the filename mapping tied to lang and item order, which is marginal value over the structured fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource with scope qualifiers ('batch-renders an ordered screenshot set for one preset and language'), which implicitly separates it from the single-shot compose_screenshot sibling. It never names a sibling explicitly, so an agent must infer the batch-vs-single boundary.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The word 'batch' and 'ordered set' imply this is the multi-item entry point versus compose_screenshot, but the description gives no explicit when-to-use, when-not-to-use, or alternative-routing guidance. Usage is only inferable from the scope wording.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns all supported platform presets with their store, exact output dimensions, and layout metrics. Call this first to decide which presets to generate.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a read-only operation by stating 'Returns...', which implies no side effects. No annotations exist, but the description adequately covers the behavior for this simple list tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that front-load the purpose and usage guidance, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description explains what is returned (store, exact dimensions, layout metrics) and provides usage context. Minor gap: could elaborate on 'platform presets', but sufficient for typical use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters in the schema, so the description does not need to add parameter details. The baseline score of 4 is appropriate as the description adds no redundancy.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns 'all supported platform presets' with specific details (store, dimensions, metrics), distinguishing it from sibling tools like compose_screenshot or generate_set which are about creation, not listing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises 'Call this first to decide which presets to generate', providing clear guidance on when to use this tool relative to other operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Checks an image against store requirements: exact preset dimensions, PNG/JPEG format, no alpha channel. Without a preset id, reports which preset the dimensions match.
| Name | Required | Description | Default |
|---|---|---|---|
| file | Yes | Path of the image to validate | |
| preset | No | Optional preset id to validate against |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key checks (dimensions, format, alpha channel) and behavior without a preset ID, but does not mention side effects, permissions, or error responses. With no annotations, more depth on return values or edge cases would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise, front-loaded sentences with no filler. Every phrase contributes meaningful information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Provides behavioral details but lacks output format or success/failure indicators. Given no output schema, the description should more clearly state what the tool returns on validation pass or failure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers both parameters fully. Description adds functional context for 'preset' (reports matching preset when omitted), enhancing understanding beyond the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Describes a specific verb ('checks') and resource ('image against store requirements'), and distinguishes from siblings by detailing validation criteria (dimensions, format, alpha channel) and behavior without a preset ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Clearly indicates when to use the tool (for validation against store requirements), but lacks explicit exclusionary guidance or comparison to sibling tools like 'list_presets' or 'compose_screenshot'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.5.0build_projectgenerate_set3 fields changedInput schema / properties / variant / $refAdded value: +"#/properties/items/items/properties/variant"Input schema / properties / variant / enumRemoved value: -[
- "text-top",
- "text-bottom",
- "tilted"
-]Input schema / properties / variant / typeRemoved value: -"string"v0.4.0compose_screenshot2 fields changedInput schema / properties / frameAdded value: +{
+ "additionalProperties": false,
+ "description": "Custom device frame. Supply your own frame PNG and the pixel rectangle where the screenshot goes; overrides the built-in frame. Omit to use the built-in frame.",
+ "properties": {
+ "image": {
+ "description": "Path to a transparent PNG device frame",
+ "type": "string"
+ },
+ "screenHeight": {
+ "description": "Screen rectangle height in the frame image, px",
+ "exclusiveMinimum": 0,
+ "type": "integer"
+ },
+ "screenWidth": {
+ "description": "Screen rectangle width in the frame image, px",
+ "exclusiveMinimum": 0,
+ "type": "integer"
+ },
+ "screenX": {
+ "description": "Left of the screen rectangle in the frame image, px",
+ "type": "integer"
+ },
+ "screenY": {
+ "description": "Top of the screen rectangle in the frame image, px",
+ "type": "integer"
+ }
+ },
+ "required": [
+ "image",
+ "screenX",
+ "screenY",
+ "screenWidth",
+ "screenHeight"
+ ],
+ "type": "object"
+}Input schema / properties / variantAdded value: +{
+ "default": "text-top",
+ "description": "Composition variant (portrait presets only): text-top = headline above a device that bleeds off the bottom; text-bottom = whole device visible with the headline underneath; tilted = text-top with the device rotated. Vary it across a set so the screenshots do not all look identical.",
+ "enum": [
+ "text-top",
+ "text-bottom",
+ "tilted"
+ ],
+ "type": "string"
+}generate_set4 fields changedInput schema / properties / frameAdded value: +{
+ "additionalProperties": false,
+ "description": "Custom device frame. Supply your own frame PNG and the pixel rectangle where the screenshot goes; overrides the built-in frame. Omit to use the built-in frame.",
+ "properties": {
+ "image": {
+ "description": "Path to a transparent PNG device frame",
+ "type": "string"
+ },
+ "screenHeight": {
+ "description": "Screen rectangle height in the frame image, px",
+ "exclusiveMinimum": 0,
+ "type": "integer"
+ },
+ "screenWidth": {
+ "description": "Screen rectangle width in the frame image, px",
+ "exclusiveMinimum": 0,
+ "type": "integer"
+ },
+ "screenX": {
+ "description": "Left of the screen rectangle in the frame image, px",
+ "type": "integer"
+ },
+ "screenY": {
+ "description": "Top of the screen rectangle in the frame image, px",
+ "type": "integer"
+ }
+ },
+ "required": [
+ "image",
+ "screenX",
+ "screenY",
+ "screenWidth",
+ "screenHeight"
+ ],
+ "type": "object"
+}Input schema / properties / items / items / properties / variantAdded value: +{
+ "description": "Per-item composition variant; falls back to the set-level variant",
+ "enum": [
+ "text-top",
+ "text-bottom",
+ "tilted"
+ ],
+ "type": "string"
+}Input schema / properties / panoramaAdded value: +{
+ "additionalProperties": false,
+ "description": "Turn the set into one continuous background: a horizontal gradient from `background` to `panorama.to` flows across all panels, so they line up as a single image in the store. Omit for solid per-panel backgrounds.",
+ "properties": {
+ "to": {
+ "description": "End color of the panoramic gradient (6-digit hex)",
+ "type": "string"
+ }
+ },
+ "required": [
+ "to"
+ ],
+ "type": "object"
+}Input schema / properties / variantAdded value: +{
+ "default": "text-top",
+ "description": "Composition variant (portrait presets only): text-top = headline above a device that bleeds off the bottom; text-bottom = whole device visible with the headline underneath; tilted = text-top with the device rotated. Vary it across a set so the screenshots do not all look identical.",
+ "enum": [
+ "text-top",
+ "text-bottom",
+ "tilted"
+ ],
+ "type": "string"
+}v0.1.0compose_screenshotcreate_showcasegenerate_setlist_presetsvalidate_screenshotScored across 6 tools
Each tool has a distinct scope: discovery (list_presets), single render (compose_screenshot), batch (generate_set), strip (create_showcase), validation (validate_screenshot), full project (build_project). The three rendering tools differ by granularity, and build_project explicitly tells the agent to prefer it over generate_set, which resolves most overlap. Only mild potential confusion remains between generate_set and compose_screenshot.
All six tools follow a consistent snake_case verb_noun pattern: list_presets, generate_set, compose_screenshot, create_showcase, validate_screenshot, build_project. The verbs vary appropriately by action while the structural convention is uniform throughout.
Six tools is well-scoped for a screenshot-generation server, covering discovery, single/batch/project rendering, showcase composition, and validation. Each tool earns its place with no redundant entries.
The surface covers a full lifecycle: preset discovery, single and batch rendering, whole-project builds with incremental re-render and cleanup of deleted outputs, showcase composition, and store-requirement validation. No obvious gaps in the screenshot-generation domain.
Create App Store screenshots, icons, ASO copy, localization, and revisions via hosted MCP.
AI-designed App Store screenshot sets from your app's screens, uploaded to App Store Connect.
Generate exact-size App Store and Google Play screenshots, feature graphics, and listing copy.
Generate designed, localized App Store screenshot sets from your raw app captures.
