Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
作者提供的说明(英文原文)
Design App Store and Google Play screenshots with your AI agent in the AppScreenStudio editor.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
在终端中运行这条命令
claude mcp add --transport http app-screen-studio https://www.appscreenstudio.com/api/mcp --header 'Authorization: your-value'运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"app-screen-studio": {
"url": "https://www.appscreenstudio.com/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"app-screen-studio": {
"type": "http",
"url": "https://www.appscreenstudio.com/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 必填 HTTP header这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过域名 appscreenstudio.com 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:Authorization
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(0.1.0)于19天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Figma Context MCP, Claude Real Video, Figma MCP Server
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
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.
The Figma MCP server brings Figma design context directly into your AI workflow.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
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.