Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Description from the maker (original English)
Design App Store and Google Play screenshots with your AI agent in the AppScreenStudio editor.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http app-screen-studio https://www.appscreenstudio.com/api/mcp --header 'Authorization: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"app-screen-studio": {
"url": "https://www.appscreenstudio.com/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"app-screen-studio": {
"type": "http",
"url": "https://www.appscreenstudio.com/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified against the domain appscreenstudio.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: Authorization
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 19 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Let your AI agent design App Store and Google Play screenshots in AppScreenStudio.
AppScreenStudio is a browser-based App Store and Google Play screenshot generator. Indie developers, mobile marketers, and ASO teams upload raw app screens, pick a template, place them in iPhone, iPad, and Android device frames, edit headlines, backgrounds, and images, then export every required store size in one click. Optional AI features handle localization, mascots, backgrounds, and assets. Nothing to install: it runs in the browser.
This repository holds the documentation and client configs for the hosted AppScreenStudio MCP server. The server itself runs on www.appscreenstudio.com, so there is nothing to build or run here.
The server connects an MCP client (Claude Code, Cursor, Codex, Gemini CLI, VS Code, and others) to the AppScreenStudio editor you have open in your browser. Your agent can read the project, add and edit cards, text, images, phones, and HTML blocks, switch templates, devices, and sizes, upload your app screens, generate AI assets and backgrounds, translate the whole set into new languages, fill in store listing text, and render a preview strip to check its own work. Every change shows up live in the editor, and you can undo it there like any other edit.
| Endpoint | https://www.appscreenstudio.com/api/mcp |
| Transport | Streamable HTTP |
| Auth | Authorization: Bearer header |
| Registry name | com.appscreenstudio/app-screen-studio |
The token belongs to your account and stays the same until you click Rotate token, which invalidates the old one. Treat it like a password.
Replace YOUR_TOKEN with the token from the editor.
claude mcp add --transport http app-screen-studio https://www.appscreenstudio.com/api/mcp \
--header "Authorization: Bearer YOUR_TOKEN"
Add this to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project). It is the same config the editor's MCP config copy button gives you.
{
"mcpServers": { "app-screen-studio": { "url": "https://www.appscreenstudio.com/api/mcp", "headers": { "Authorization": "Bearer YOUR_TOKEN" } } } }
Add this to ~/.codex/config.toml:
[mcp_servers.app-screen-studio]
url = "https://www.appscreenstudio.com/api/mcp" bearer_token_env_var = "APPSCREENSTUDIO_MCP_TOKEN"
Then export the token in the shell that runs Codex:
export APPSCREENSTUDIO_MCP_TOKEN="YOUR_TOKEN"
gemini mcp add -t http -H "Authorization: Bearer YOUR_TOKEN" app-screen-studio https://www.appscreenstudio.com/api/mcp
Or add this to ~/.gemini/settings.json:
{
"mcpServers": { "app-screen-studio": { "httpUrl": "https://www.appscreenstudio.com/api/mcp", "headers": { "Authorization": "Bearer YOUR_TOKEN" } } } }
Add this to .vscode/mcp.json. VS Code asks for the token once and stores it securely.
{
"inputs": [ { "type": "promptString", "id": "appscreenstudio-token", "description": "AppScreenStudio MCP token (editor: Connect Your Agent, MCP Details)", "password": true } ], "servers": { "app-screen-studio": { "type": "http", "url": "https://www.appscreenstudio.com/api/mcp", "headers": { "Authorization": "Bearer ${input:appscreenstudio-token}" } } } }
Any MCP client that supports Streamable HTTP with custom headers works. Point it at https://www.appscreenstudio.com/api/mcp and send Authorization: Bearer YOUR_TOKEN.
| Tool | What it does |
|---|---|
get_editor_snapshot | Read one platform of the open editor. |
update_text | Update a text layer on a screenshot in the open editor. |
add_text | Add a text layer to a screenshot in the open editor. |
remove_text | Remove a text layer from a screenshot in the open editor. |
add_screenshot | Add a card to the end of a platform set. |
update_screenshot | Update a card and its main phone: background, phone placement and app screen, pattern, fade, or shadow. |
remove_screenshot | Remove a screenshot from the open editor. |
add_asset | Add an image layer to a card. |
update_asset | Update an image layer on a screenshot in the open editor. |
remove_asset | Remove an image layer from a screenshot in the open editor. |
add_div | Add a box layer to a card. |
update_div | Update a box layer on a card. |
remove_div | Remove a box layer from a screenshot in the open editor. |
add_phone | Add another phone to a screenshot card in the open editor. |
update_phone | Update an extra phone added with add_phone. |
remove_phone | Remove an extra phone added with add_phone. |
reorder_element | Move a layer one step forward or backward among layers of the same kind. |
set_template | Set the template of the open project. |
update_template_color | Update one color of the open project's template. |
set_resolution | Set the pixel size of a platform set. |
set_device | Set the device of a platform set. |
set_phone_color | Set the device color of a platform set. |
set_show_notch | Show or hide the notch on a platform set. |
set_squircle_frame | Enable or disable the squircle frame on a platform set. |
set_link_texts | Link or unlink matching text layers across platform sets. |
rename_project | Rename the open project. |
undo | Undo the last edit in the open editor. |
redo | Redo the last undone edit in the open editor. |
search_google_fonts | Search Google Fonts by family name, category, or both. |
add_project_font | Add a Google Fonts family to the open project. |
list_library | List assets or mascots saved on this account (not screenshots or backgrounds). |
get_sprite | Return one saved asset or mascot in the same shape as a list_library item, including spriteSheet and poses. |
generate_asset | Generate an asset sprite with AI and save it to the account library. |
generate_mascot | Generate a mascot sprite with AI and save it to the account library. |
generate_background | Generate an AI background for one card. |
update_store_listing | Update App Store or Google Play listing fields for the current language. |
capture_platform_strip | Return one JPEG of every card in a platform set side by side, as the editor renders them. |
upload_image | Prepare an image upload for the open project. |
duplicate_screenshot | Duplicate a screenshot and insert the copy immediately after it. |
copy_screenshot | Copy a screenshot onto another platform set. |
move_screenshot | Move a screenshot left or right within its platform set. |
set_language | Switch the open editor to a language that already exists on the project. |
ai_translate | Add up to 5 languages by translating the open language with the same AI localize flow as the editor. |
add_platform_set | Add a platform set to the open project. |
remove_platform_set | Remove an extra platform set. |
set_project_background | Set or clear the project background image. |
set_realistic_frame | Enable or disable the realistic device frame on a platform set. |
report_mcp_feedback | Report a bug, an unexpected tool result, or a suggestion about these MCP tools, when you notice one. |
rate_this_mcp | Rate how well these MCP tools worked for the task you just finished, from 1 to 5 stars. |
AI tools (generate_asset, generate_mascot, generate_background, ai_translate) spend AppScreenStudio AI credits from your account.
The documentation and config files in this repository are released under the MIT License. The AppScreenStudio service, the hosted MCP server, and the AppScreenStudio name and assets are not covered by this license.