Generate App Store Screenshots With Claude Code
Connect Screenies' remote MCP server to Claude Code and generate, localize, and download a full App Store screenshot set from prompts, with no local build to run.
On this page
You can generate a full App Store screenshot set from inside Claude Code by connecting Screenies' remote MCP server: run one claude mcp add command, sign in through the browser once, then ask the agent to upload your screens and generate the set. This guide walks that setup and the prompt-driven workflow it opens, then draws the line between it and the local Claude Code skills that also rank for this search.
Search this exact phrase and the results split into two camps that behave very differently, so it's worth sorting them before you install anything. Most of the top results are skills: markdown-and-script bundles like ParthJadhav's app-store-screenshots, which scaffolds a Next.js editor into your repo, or Adam Lyttle's ASO skill, which reads your codebase and assembles frames locally, often leaning on fastlane for the device mockups. The other camp is remote MCP servers, where the generation runs on someone's hosted service and the agent just calls tools over a connection: AppLaunchFlow and AppScreenshotStudio both offer that, and Screenies sits here too. The two camps trade off in a clean way. A local skill gives you the files and full control but leaves the design, the spec upkeep, and any build errors on your machine; a hosted server hands off all of that and asks only that you sign in.
Skills that scaffold versus servers that generate
The practical difference shows up the first time something breaks. A skill that scaffolds a Next.js editor means you now own a small web app: its dependencies, its render step, and whatever the image model decided your captions should say, all sitting in your working tree. That's the right trade if you want to hand-tune every pixel and keep the source. A hosted MCP server keeps none of that on your side, so there's no local render to debug and no generated code to review, at the cost of the artwork living on the service rather than in your repo. Screenies' MCP server is the hosted kind: the same generation that runs in the web dashboard, exposed to your agent as tools. If you'd rather read the tool list and connect from a client page, the per-client setup pages cover Claude Code, Claude.ai, and Cursor.
Connecting the server to Claude Code
Setup is a single command you paste into your terminal:
claude mcp add --transport http screenies https://screenies.app/mcp
Then run /mcp inside a Claude Code session, pick screenies, and the agent opens a browser window where you sign in to Screenies and approve the connection. That's OAuth 2.1 doing the work: your agent never sees your password, the tools are scoped to your own workspaces and apps, and you can revoke access whenever you like. There are no API keys to paste or rotate. Any other client that speaks remote MCP takes the same URL, so the Cursor and Claude.ai flows differ only in where you enter it.
Generating a set from prompts
Once connected, the whole set runs from the chat. Tell the agent what you're launching and it walks the tools in order: list_apps to find or place your app, request_screenshot_upload to get signed URLs for your raw captures, then generate_screenshot_set to start the run against your uploaded screens and a short description of what the app does and why it's worth downloading. Generation is asynchronous, so the agent polls get_batch_status until the slides finish, and each completed slide comes back with a download URL. If a slide fails, regenerate_failed retries just that one, and failed generations refund their credit automatically. A typical prompt is as plain as "upload these five screens, generate a set for a habit tracker aimed at people who keep quitting," and the agent handles the tool calls from there.
One property matters more than convenience here: the source UI in each slide is your real screen, composited into an Apple device frame in code. The image model paints only the background art behind it, never the app interface. That guardrail is the difference between a listing that passes review and the failure mode developers keep hitting, where a generator redraws the UI and the submission gets rejected for not matching the actual app under guideline 2.3.3. What the agent controls is the pitch around your screens: slide order, the headline on each slide, and a set-wide palette pulled from your UI. What it can't do is invent functionality you don't have.
Localizing and editing without leaving the terminal
Revisions are tools too, so you don't drop back into a design app to fix a word. edit_headline rewrites the caption on one slide, reorder_set changes the sequence and drags any localized copies along with it, and headline edits after generation don't spend credits. When the English set is right, localize_set translates it into other App Store locales; because it reuses the artwork instead of calling the image model again, adding a fifth language costs 0.1 credits per size rather than a fresh generation. You can check get_credit_balance before a big run if you're watching the meter. Everything you started in Claude Code stays on the same account, so you can open the dashboard later and the app, its set, and its credits are all there.
Cost, and what the connection doesn't change
The MCP server is included with every Screenies account, and generation started from your agent spends the same credits as generation started in the dashboard: one credit per generated screenshot at a 6.9-inch iPhone size, edits free, localization at 0.1 credits per size. It adds no output the web app lacks, so it's iPhone screenshots only right now, at the exact sizes App Store Connect accepts, with iPad not shipped yet and no Google Play output. The pricing page carries the subscription and the one-time credit packs, neither of which the server changes.
Questions about the agent workflow
Do I need to run a local server or write any code?
No. Screenies' MCP server is remote and hosted, so the one claude mcp add command and an OAuth sign-in are the entire setup. Nothing gets scaffolded into your repository and there's no dev server to keep running.
Does generating through Claude Code cost more than the dashboard?
The cost is identical to the dashboard. The server is included with your account, and a screenshot generated from a prompt draws one credit exactly as it would from the web app. Credits never expire regardless of where you spend them.
Can the agent make up screens my app doesn't have?
No, it can't do that. Every slide places your uploaded, real capture into the device frame in code, and the model only generates the background behind it. That's what keeps the output inside Apple's rule against screenshots that misrepresent the app.
Which agents work besides Claude Code?
Any client that supports remote MCP servers. The same https://screenies.app/mcp URL connects Claude.ai and Cursor, and the MCP server page lists the current clients with their setup steps.
Can I start in the terminal and finish in the browser?
Yes. The tools act on your normal Screenies workspace, so a set you generate from Claude Code opens in the dashboard for hand-editing, reordering, or download like any other.
Does it output iPad or Google Play sizes?
No. Output is the 6.9-inch iPhone set that App Store Connect requires; there's no Google Play output, and iPad isn't shipped yet. The full iPhone size matrix is on the sizes page.
Point your agent at it
If Claude Code is already where you build, add the server and let the same session that ships your app also draft its listing: connect the MCP server or sign in to Screenies first and generate a set from your real screens.