프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. Google로 로그인하면 리뷰를 쓸 수 있어요.프로토타입 · 30분마다 업데이트
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

PopNow

제작자: popnow-ai버전 0.2.2i★ 1i클라우드에서 실행공식 사이트 ↗
레지스트리 이름io.github.popnow-ai/popnow-mcp

설치 방법

What it does

AI image, video, music and speech generation: text-to-video, image-to-video, effects and upscaling.

  • Connects 클라우드에서 실행
  • Account or key Sign in to the service when you connect (OAuth)
  • Category 디자인, 이미지 및 오디오

함께 쓰기

이런 작업을 AI에게 가르치는 Skill, 이것과 함께 쓸 수 있습니다

impeccable

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

제작자: pbakaus★ 112,544skill 1개

Skill · 안내서

diagram-design

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.

제작자: cathrynlavery★ 68,069skill 1개

Skill · 안내서

frontend-slides

Create beautiful slides on the web using a coding agent's frontend skills

제작자: zarazhangrui★ 32,514skill 1개

Skill · 안내서

이 순위인 이유

목록은 사용 점수(100점 만점)로 정렬되며 구성은 다음과 같습니다

인기4/80GitHub 별 또는 주간 다운로드: 큰 쪽 60, 작은 쪽 20
최신성12/1230일 안에 릴리스나 코드 변경이 있으면 만점
응답 중8/8마지막 점검 때 클라우드 엔드포인트가 응답
사용 점수24/100

품질: 기본 점검 5/5개 통과(표시만, 정렬에는 안 씀) · 상승세: 데이터 없음 (급상승 탭에서만 사용)

설치

쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.

한 문장으로 AI에게 설치 맡기기

PopNow 설치해 줘. https://mcp.popnx.com/i/popnow-ai-popnow-mcp.md 를 따라 하고, 명령을 먼저 보여 주고 내가 승인하면 실행해.

내 컴퓨터에서 작업하는 AI(Claude Code, Cursor 등)에 붙여 넣으세요. 단계를 읽고 명령을 보여 준 뒤 승인을 기다립니다. 키도 가입도 필요 없습니다. · AI가 읽을 전체 내용 보기

검사 5/5 통과 · 내가 묻는 내용은 제작자 서버(api.popnow.ai)를 거쳐요 · ✓ 명령 확인 2026년 11월 13일

먼저: 어떤 AI를 쓰시나요?

쓰는 앱을 고르면 아래에 단계가 나옵니다.

Claude에 연결할 수 있어요 · 약 2분

키 필요 없음, 설치 필요 없음 · claude.ai나 데스크톱 앱에서 한 번 설정하면 채팅에서 쓸 수 있어요 · 무료 계정은 1개까지 · Team/Enterprise는 소유자(Owner)가 추가

  1. Claude의 Connectors 페이지 열기

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. “Add” → “Custom” → “Web”를 누르고 이 2칸 채우기

    여기서 복사해 Claude의 같은 이름 칸에 붙여 넣고 Continue를 누르세요

    Name · 이름PopNow
    Remote MCP server URL · 주소https://api.popnow.ai/mcp

    Claude가 찾은 로그인 설정 화면에서 Continue를 누르고 · Authentication은 제작자 안내대로(Sign in now, Sign in when needed, No sign in) 고른 뒤 Add를 누르세요

  3. 채팅에서 켜기

    +ConnectorsPopNow

  4. 해 보기

    PopNow을 써서 나에게 무엇을 해 줄 수 있는지 알려 주고, 하나 해 봐

    ✓ Claude가 PopNow을 쓰고 있다고 하거나 답에 PopNow 도구 이름이 나오면 연결된 거예요

메뉴 이름은 2026년 11월 11일에 Anthropic 도움말에서 확인 · 앱 버전에 따라 화면이 조금 다를 수 있어요

ChatGPT 연결은 요금제에 따라 달라요

전체 MCP: 웹 ChatGPT Business, Enterprise, Edu · Pro: 읽기/가져오기 권한으로 연결, 데이터를 바꾸는 도구는 안 될 수 있어요 · Plus: 공식 문서 미확인, 플러그인 화면에 사용자 지정 MCP 추가 항목이 보이면 시도해 볼 수 있어요 · 웹만

  1. 웹 ChatGPT에서 MCP 추가 페이지 열기

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 이름과 주소 입력

    이름을 넣고 Connection에 주소를 붙여 넣은 뒤 경고에 체크하고 Create as a plugin을 누르세요

    Name · 이름PopNow
    Connection · 주소https://api.popnow.ai/mcp
  3. 채팅에서 PopNow 고르기

    새 채팅을 열고 입력 전에 플러그인 목록에서 PopNow을 고르세요

  4. 해 보기

    PopNow을 써서 나에게 무엇을 해 줄 수 있는지 알려 주고, 하나 해 봐

    ✓ ChatGPT가 PopNow을 쓰고 있다고 하거나 답에 PopNow 도구 이름이 나오면 연결된 거예요

메뉴 이름은 2026년 11월 11일에 OpenAI 도움말에서 확인 · 앱 버전에 따라 화면이 조금 다를 수 있어요

Claude Code에 연결할 수 있어요 · 약 2분

키 필요 없음, 설치 필요 없음

  1. 터미널 열기

    Mac: Command+스페이스를 누르고 Terminal 입력 · Windows: PowerShell 열기

  2. 이 명령을 붙여 넣고 Enter

    claude mcp add --transport http --scope user popnow https://api.popnow.ai/mcp
  3. Claude Code에서 /mcp 입력

    PopNow이 목록에 있고 연결됨으로 보이면 돼요

  4. 해 보기

    PopNow을 써서 나에게 무엇을 해 줄 수 있는지 알려 주고, 하나 해 봐

    ✓ Claude Code가 PopNow을 쓰고 있다고 하거나 답에 PopNow 도구 이름이 나오면 연결된 거예요

메뉴 이름은 2026년 11월 11일에 Anthropic 도움말에서 확인 · 앱 버전에 따라 화면이 조금 다를 수 있어요

Cursor에 연결할 수 있어요 · 약 2분

키 필요 없음, 설치 필요 없음

  1. 이 버튼으로 Cursor 열기

    Cursor에서 열기

    Cursor가 설치를 확인하면 Install을 누르세요

  2. Cursor에서 AI 채팅을 Agent 모드로 열기

  3. 해 보기

    PopNow을 써서 나에게 무엇을 해 줄 수 있는지 알려 주고, 하나 해 봐

    ✓ Cursor가 PopNow을 쓰고 있다고 하거나 답에 PopNow 도구 이름이 나오면 연결된 거예요

메뉴 이름은 2026년 11월 11일에 Cursor 도움말에서 확인 · 앱 버전에 따라 화면이 조금 다를 수 있어요

VS Code에 연결할 수 있어요 · 약 2분

키 필요 없음, 설치 필요 없음

  1. 이 버튼으로 VS Code 열기

    VS Code에서 열기

    VS Code가 설치를 확인하면 Install을 누르세요

  2. VS Code에서 AI 채팅을 Agent 모드로 열기

  3. 해 보기

    PopNow을 써서 나에게 무엇을 해 줄 수 있는지 알려 주고, 하나 해 봐

    ✓ VS Code가 PopNow을 쓰고 있다고 하거나 답에 PopNow 도구 이름이 나오면 연결된 거예요

메뉴 이름은 2026년 11월 11일에 VS Code 도움말에서 확인 · 앱 버전에 따라 화면이 조금 다를 수 있어요

Windsurf, Zed, Gemini CLI 같은 다른 MCP 앱은 추가 방법이 저마다 달라요. 앱 목록에서 확인하세요

MCP를 쓰는 앱 모두 보기 →

웹으로 연결하는 앱용 주소

주소https://api.popnow.ai/mcp

JSON 설정은 아래 “개발자용”에 있어요

막혔나요? PopNow을 쓰는 사람에게 물어보세요💬 토론 →
개발자용: 터미널 명령과 JSON 설정

웹으로 연결

Claude Code

claude mcp add --transport http --scope user popnow https://api.popnow.ai/mcp

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "popnow": {
      "url": "https://api.popnow.ai/mcp"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "popnow": {
      "type": "http",
      "url": "https://api.popnow.ai/mcp"
    }
  }
}

이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.

한눈에 보기

주간 다운로드i
npm/PyPI에 없음
연결 방식
클라우드에서 실행
전송 방식
streamable-http
최신 버전i
0.2.2
레지스트리 공개i
2026년 11월 6일
코드 마지막 변경i
2026년 11월 14일
마지막 확인
2026년 11월 18일
제작자
popnow-ai
웹사이트
popnow.ai
레지스트리 상태
활성

어떤 앱에서 쓸 수 있나요

이 서버의 연결 방식과 각 앱의 공식 문서를 바탕으로 했어요. 2026년 11월 10일 확인.

인터넷으로 연결하는 앱

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

모든 앱과 장단점 →

할 수 있는 일

서버가 도구 목록을 보여 주기 전에 로그인을 요구해요.

기본 점검i

누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 19일 점검

  • ✓ 통과

    제작자와 저장소 일치

    레지스트리 이름이 GitHub 계정 popnow-ai 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요

  • ✓ 통과

    계속 관리되고 있음

    코드 마지막 변경: 5일 전

  • ✓ 통과

    라이선스 있음

    MIT 사용

  • ✓ 통과

    엔드포인트 응답

    103ms 만에 응답(HTTP 401)

  • ✓ 통과

    OAuth로 로그인

    OAuth 로그인을 지원한다고 밝혀서, AI 앱이 로그인 화면으로 안내해 줘요

  • … 아직 점검 안 함

    도구 설명에 숨겨진 지시 없음

    아직 점검하지 않았어요. 엔드포인트를 점검할 때 도구 목록을 읽어요

우리가 확인하는 것 → · JSON

제작자: 재확인 요청 또는 잘못된 정보 신고
제작자용: README에 배지 달기

제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/popnow-ai-popnow-mcp.svg)](https://mcp.popnx.com/en/servers/popnow-ai-popnow-mcp)

토론

질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.

아직 글이 없어요. 처음으로 질문하거나 공유해 보세요.

이곳의 글은 사용자가 쓴 것으로, PopNx 팀의 글이 아니에요.

로그인하고 글쓰기

사용자 리뷰

아직 리뷰가 없어요

로그인하고 리뷰 쓰기

디자인, 이미지 및 오디오 카테고리의 다른 서버와 비교i

  • 이 카테고리의 다른 서버 3275개 중 78%보다 스타가 많아요
  • 이 카테고리의 다른 서버 3275개 중 72%보다 최근에 레지스트리에 공개됐어요
  • 기본 점검 결과가 이 카테고리의 다른 서버 3275개 중 99%와 같거나 더 좋아요

레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.

자주 묻는 질문

PopNow, 안전한가요?

해당하는 기본 점검 5개 중 5개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.

어떤 키나 코드가 필요한가요?

레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.

내 컴퓨터에서 실행되나요, 클라우드에서 실행되나요?

제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.

아직 관리되고 있나요?

GitHub 저장소는 마지막으로 5일 전 변경됐고, 최신 버전(0.2.2)은 13일 전 레지스트리에 올라왔어요.

어떤 앱에서 쓸 수 있나요?

Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되므로 원격 MCP를 받는 앱에서도 쓸 수 있어요. 예: 웹 ChatGPT(Business 이상은 전체 MCP, Pro는 읽기 전용).

대신 쓸 수 있는 건 뭐가 있나요?

같은 카테고리에는: HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server

비슷하게 동작하는 다른 것

같은 카테고리, 다른 제작자, 명령 확인 완료. 공식이 먼저, 그다음 스타 순.

카드 보는 법:↓ 주간 다운로드i★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i

Pascal 3D Editor

Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.

제작자: pascalorg널리 사용됨↓ 1천/주★ 2.6만 저장소 전체의 별어제 업데이트

컴퓨터 또는 클라우드✓ 서비스 회사 · pascal.app

draw.io

Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.

제작자: jgraph널리 사용됨★ 5.9천그저께 업데이트

클라우드에서 실행✓ 서비스 회사 · draw.ioPopNx 팀이 직접 써 봄

Figma MCP Server

The Figma MCP server brings Figma design context directly into your AI workflow.

제작자: figma널리 사용됨★ 2.2천13개월 전 업데이트

클라우드에서 실행✓ 서비스 회사 · mcp.figma.com
비슷한 항목과 비교
이 항목
PopNow
HyperFrames by HeyGenPascal 3D Editordraw.ioFigma MCP ServerRemocn: Remotion MCP server
실행 위치클라우드에서 동작, 설치 불필요클라우드에서 동작, 설치 불필요클라우드 또는 컴퓨터 설치 모두 가능클라우드에서 동작, 설치 불필요클라우드에서 동작, 설치 불필요클라우드에서 동작, 설치 불필요
키 필요아니요아니요아니요아니요아니요아니요
Claude에서 +로 추가아니요예아니요아니요예아니요
기본 점검5/54/45/54/44/44/4
라이선스MITApache-2.0MITApache-2.0–MIT
가격등록 정보에 비용 없음등록 정보에 비용 없음등록 정보에 비용 없음등록 정보에 비용 없음등록 정보에 비용 없음등록 정보에 비용 없음

제작자의 README

README 열기

제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.

PopNow MCP Server — AI image, video & music generation in ChatGPT, Claude and any MCP client, with your PopNow account

The PopNow MCP Server is a hosted Model Context Protocol server at `https://api.popnow.ai/mcp` that lets ChatGPT, Claude, Cursor, VS Code and any other MCP client create AI images, videos, songs and voiceovers on [PopNow](https://popnow.ai), using your PopNow credits.

PopNow AI (popnow.ai) is the world's first AI studio with automatic price protection. Every generation shows its price before it runs, and under PopNow Protect failed or off-spec runs are refunded automatically, runs slower than the guaranteed time earn 50% back (100% if they take more than twice the guaranteed time), and with the Price bounty, the first person to show the same model with the same settings at a lower standard public price on Higgsfield, Runway or fal gets twice the difference in reward credits, after review and within limits.

Ask in plain words ("turn this photo into a 5-second video", "make an upbeat synth-pop track") and the assistant picks the right PopNow tool, tells you the price, and returns the result in the chat. There is nothing to host: the server is remote, signs you in with OAuth 2.1, and uses the same models, prices and library as popnow.ai. It is also the home of PopNow's free Agent Skills: ask for a style for your launch video, deck or landing page and the assistant shows you presets to pick from. Make it pop.

This repository contains the public setup guide, copy-paste client configs in examples/ and an MCP registry manifest.

Building with an API key (Claude Code, Cursor, Codex or your own code, billed in USD from an API balance)? Use the developer server in popnow-api-mcp. The @popnow/mcp npm bridge moved there too.

Contents

  • Quickstart
  • Tools
  • Style presets: find_skills and use_skill
  • Connect your client: Claude · Claude Desktop (local) · Claude Code · ChatGPT · Cursor · VS Code · Windsurf · Cline · Codex CLI · Other clients
  • Hermes Agent and Gemini CLI extensions
  • Authentication
  • Credits, prices and confirmation
  • Example prompts
  • Troubleshooting
  • FAQ

Quickstart

  1. Copy the server URL: https://api.popnow.ai/mcp
  2. Add it to your client as a remote (Streamable HTTP) MCP server. For example, in Claude Code:
   claude mcp add --transport http popnow https://api.popnow.ai/mcp
  1. Sign in and ask. Your client opens a PopNow sign-in page the first time; press Allow, then ask for a picture, a video or a song.

No PopNow account yet? Sign up at popnow.ai and pick a credit pack when you need more credits.

Server URLhttps://api.popnow.ai/mcp
TransportStreamable HTTP, stateless (POST only; GET and DELETE return 405)
Sign-inOAuth 2.1 with PKCE and dynamic client registration: you sign in with your PopNow account
Scopesgenerate (create with your credits) and read (balance, creations, model list)
ToolsGeneration, account and style-preset tools (listed below)
PriceSame credits as popnow.ai (1 credit = $0.001). Up to 300 credits starts at once; anything above waits for your yes. Style presets are free

Tools

ToolWhat it doesKey parametersTypical cost
create_imageMake a new picture from a descriptionprompt, aspect_ratio (default 1:1), model, max_creditsabout 48 credits (default Nano Banana 2.1)
edit_imageChange a photo with words: new style, outfit, background, add or remove thingsprompt, image_url / image, more_image_urls, aspect_ratio, model, max_creditsabout 48 credits
create_videoMake a short video from a description, or bring a photo to life (text-to-video and image-to-video)prompt, image_url / image, duration_seconds (default 5), aspect_ratio (default 16:9), model, max_creditsabout 185 credits for 5 s (default MiniMax H3); 1 to 3 minutes
create_musicMake an original song or instrumental trackprompt, lyrics, instrumental, voice (female / male), title, max_creditsabout 72 credits per song (Suno v6)
create_speechTurn text into natural speech in many voices and languagestext, voice (Kore, Puck, Charon, Aoede, Fenrir, Leda ...), style (whisper, empathetic, vocal_smile, newscaster, promo_hype, deadpan), max_creditspriced by length, about 20 credits per minute of audio
apply_effectTurn a photo into a trending effect video (Zombie Turn, Flying Car, Tiny Planet, Molten Gold, Hyperdrive ...) or a photo makeover (Clay Figure, Pixel Art ...)effect (name or id), image_url / image, max_creditsabout 125 to 340 credits per video, 30 to 50 per photo makeover; quoted first
remove_backgroundCut out the subject and make the background transparentimage_url / image, max_creditsabout 5 credits
upscaleMake a photo or video sharper and biggerimage_url / image or video_url, size (photos 2k, 4k, 8k; videos 720p, 1080p, 2k, 4k), max_creditsabout 12 credits for a photo; videos by length
get_jobCheck on a creation that is still running and return it when readyjob_id, wait_seconds (0 to 50, default 30)free
list_my_creationsShow your recent PopNow creations with linkskind (image, video, audio), limit (1 to 20, default 10)free
check_balanceShow how many credits you have left (and how many are held for running jobs)nonefree
list_modelsList the image, video and audio models, or every effect, with pricescategory (image, video, audio, effects)free
find_skillsFind ready-made style presets (Agent Skills) for what you want to make: product launch videos, slide decks, landing pages and websites, editorial images. Each option has a name, a one-line look, a preview video or picture, the PopNow generation it uses and what it needs locallyintent (your words), type (video, image, slides, web), limit (1 to 6, default 4)free
use_skillGet the preset you picked: its full playbook (SKILL.md), a short-lived signed download link for the whole package with install commands for your coding agent, and which PopNow tools run its generation stepsslug (from find_skills), agent (claude-code, codex, cursor, gemini-cli, github-copilot, opencode, or chat without a file system)free; each generation it runs is quoted first
  • Models. Every generation tool that takes model accepts a PopNow model id from list_models, so "use Seedance" or "make it with Wan" just works. Models include Kling, Seedance, Wan, Vidu, MiniMax, Nano Banana, GPT Image, Flux, Suno and more; the live list is always list_models.
  • Photos in. image_url takes a public https link or a popnow:// link from an earlier result. In ChatGPT, an attached photo arrives as the image file object.
  • Results out. Images come back inline as a preview plus a download link; videos and audio come back as links. Each result also has a permanent popnow:// link you can pass to another tool ("now animate that picture"). Everything is saved in your PopNow library.
  • Annotations. All tools carry the standard MCP hints. get_job, list_my_creations, check_balance, list_models, find_skills and use_skill are read-only, and no tool deletes anything.
  • Effects cover the same set as the Effects page. Two-person effects need two placed photos and are website-only.

Style presets: find_skills and use_skill

PopNow keeps a catalog of free Agent Skills: named styles for product launch videos, slide decks, landing pages and websites, editorial images and more, each with a preview and a full playbook that an AI agent follows to build the result. Two free tools bring the catalog into any MCP client:

  1. Find. The assistant calls find_skills with what you want to make, in your words (optionally type: video, image, slides or web). It gets up to 6 options (4 by default), best first, each with a name, a one-line description of the look, a preview link, the PopNow generation it uses and its local requirements.
  2. Pick. The assistant shows you the options with their previews and asks which one you want.
  3. Use. The assistant calls use_skill with the chosen slug and agent (claude-code, codex, cursor, gemini-cli, github-copilot, opencode, or chat in apps without a file system). The reply holds the full SKILL.md playbook, a short-lived signed download link to the complete package with the install commands for that agent, and which PopNow tools (create_image, create_video, create_music, create_speech ...) replace the playbook's own generation scripts.

Finding, downloading and using a preset is free. Only the images, video, music or voice it generates cost credits, quoted and confirmed like every other PopNow tool. Presets are licensed for your own and client work; please don't republish the packages. In a chat app without a file system the assistant can still follow the playbook's look and make the pictures with create_image; steps that run local scripts need a coding agent.

You:        I need a launch video for our note-taking app.

Assistant: (calls find_skills with intent "launch video for a note-taking app", type "video") Here are three styles:

  1. - . Preview: . Uses PopNow video; needs Node.js.
  2. - ...
  3. - ... Which one do you like? The preset is free; only the clips it makes cost credits.

You: The first one. Assistant: (calls use_skill with that slug and agent "claude-code", installs the package from the signed link, then follows the playbook) Installed. The first clip will cost 185 credits. Go ahead? You: Yes. Assistant: (calls create_video with max_credits: 185, then get_job, and keeps building the video)

You can also browse the catalog and its previews on the website; Use a skill in ChatGPT or Claude walks through it.

Connect your client

Every client below talks to the same remote server and signs in with your PopNow account (OAuth). Ready-made files are in examples/.

Claude (web, d

앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요