Skip to main content
Model Context Protocol

The ScreenMocks MCP server

Point Claude, Cursor, VS Code, Codex or ChatGPT at ScreenMocks and let it build the whole App Store gallery: real device frames, every canvas size Apple asks for, and 48 locales, over your own projects.

Read the docs arrow_forward
ClaudeCursorCodexGeminicodeVS CodeboltZapier
The surface

Anything you can do,
an agent can do.

45 tools, and the standard they are held to is parity with the editor.

Full reference arrow_forward

Screen builder

Text, shapes, device frames and groups on a real canvas.

add_layers · update_layer · align_layers

48 App Store locales

Add a language and the whole set follows. Override one cell.

set_languages · set_translations

Every store canvas

iPhone, iPad, Android and any size you add. Each owns its screens.

add_size · list_size_screens

33 device frames

A frame follows the canvas: an iPhone on the Play tab draws a Pixel.

list_catalog · update_layer

Status bars

Four real bars, laid over a capture that came without chrome.

set_status_bar

Your captures, in bulk

Point at a folder and they fill every empty display in order.

import_asset_from_url · set_screenshot

Stock and icons

Pexels photography and 90k vectors, searched from the agent.

search_stock_photos · search_icons

The template library

Start from a designed set, or take one screen out of another.

apply_template · add_template_screens

Export and push

Every size and locale zipped, or straight to App Store Connect.

export_project

What it does

One prompt in.
A finished gallery out.

See the templates arrow_forward

You, in Claude

Make an App Store set for my app from the Atlas template. Use the five captures in ./screenshots, write the headlines yourself, then add Spanish and Japanese and export the iPhone and iPad canvases.

checkCreated the project and pulled the templatecheckPlaced five captures, one per screencheckWrote and translated the headlinescheckExported 2 canvases x 3 locales
Connect

Three lines in your client config.

{ "mcpServers": { "screenmocks": { "type": "http", "url": "https://www.screenmocks.com/api/mcp", "headers": { "Authorization": "Bearer sf_pat_your_token" } } } }
Server name
screenmocks
Endpoint
https://www.screenmocks.com/api/mcp
Transport
Streamable HTTP. It is a remote server, so there is nothing to install and nothing to run locally.
Authentication
Authorization: Bearer <token> — A personal access token minted in your account. Every token starts sf_pat_.
Tools
45, covering projects, screens, layers, text, localization, assets, previews and export.
Availability
Every paid plan: Pro monthly or yearly, and the Launch Pass bought once. The free plan cannot mint a token.
Tokens per account
5 at a time, one per client. There are no seats and no team model.
Documentation
https://www.screenmocks.com/mcp

Questions

Does ScreenMocks have an MCP server?

Yes. ScreenMocks runs a remote Model Context Protocol server at https://www.screenmocks.com/api/mcp, over the streamable HTTP transport. It exposes 45 tools covering everything the editor can do to a project: create projects, add screens and layers, style and align them, write captions, manage languages and canvas sizes, set screenshots, and reach the icon, stock photo and template libraries.

Which MCP clients does it work with?

Any client that speaks the streamable HTTP transport, including Claude Code, Claude Desktop, Cursor, VS Code, Codex and ChatGPT developer mode. There is nothing to install: it is a remote server, so a client only needs the URL and an access token.

How do I authenticate?

With a personal access token sent as an Authorization: Bearer header. Mint one in ScreenMocks under Settings, MCP access. The token is shown once, when it is created, and can be revoked at any time.

Do I need a paid plan to use the MCP server?

Yes. The MCP Connector is on every paid plan: Pro at $9.99 a month or $74.99 a year, and the Launch Pass at $149 once. The free plan can use the editor without limits but cannot mint an access token.

How many access tokens can one account hold?

Five at a time, one per client: an editor, a second machine, a CI job. There are no seats and no team model, so the five tokens belong to the one account that made them.

Can an agent see what it designed?

Yes. render_preview returns real images of the screens inline, rendered from the same document the export renders, and get_project with layout: true returns measured boxes, overflow, overlaps and legibility findings. Between them an agent can check its own work instead of reporting success blindly.

How do screenshots reach a project through MCP?

Image bytes never travel inside a tool call. An agent either imports a picture from a public URL with import_asset_from_url, or asks for a signed upload URL with create_upload_url and puts the file there itself. Either way it becomes an ordinary asset in the account.

Can an agent reach another account with my token?

No. Every tool runs against a project store bound to the token owner, so addressing another account is not expressible. Projects stay private to the account that owns them, and revoking a token cuts the client off immediately.

Wire it up once.
Ship every set from a prompt.

The connector is on every paid plan, the one-time pass included.

Read the docs