Poppify Studio
Photo-to-reel MCP for solo founders and SMBs. Upload 1–10 photos and get a captioned vertical reel for Instagram, TikTok, YouTube Shorts, or Facebook — with motion, library-matched music, and optional AI voiceover.
README
Poppify — Photo to TikTok & Instagram Reels (MCP Server + Claude Code Plugin)
MCP server and Claude Code plugin for photo to TikTok, Instagram Reels, YouTube Shorts, and Facebook video. Upload 1–10 photos, get a captioned 15/30/60s reel with motion, library-matched music, and optional voiceover. $0.06 base render. 50 free seeds on signup. No subscription.
Poppify is a Claude Code plugin (and standalone MCP server) that composes reels via a photo-led creative pipeline (FFmpeg motion + library-first asset matching + recipe-driven narrative + on-screen text), not a text-to-video generator. That's why the base render is 1 seed (~$0.06) instead of dollars-per-second like generative video services (Runway, Sora, Kling, Vidu, Veo). When you need standalone AI assets, generate_image / generate_music / generate_voiceover are callable on their own (10 seeds each).
Where it fits in a Claude Code marketing stack: Poppify is the creative slot. Pairs with Postiz for cross-platform scheduling and Windsor.ai for attribution. Drop-in replacement for Runway when you have photos and want library-matched audio; use HyperFrames when you want to code video in HTML.
Not for: text→video generation (Sora, Veo, Kling — use Runway or a generative video MCP), avatar-based video (use HeyGen / Synthesia), 4K horizontal cinema, or sub-4-second clips.
Built for: SMBs (5–19 employees) and solo service providers who want consistent vertical reels without hiring a content creator. The agency replacement at $30–60/mo instead of $3K+.
What's inside
| Component | Purpose |
|---|---|
MCP server (https://poppify.ai/mcp, HTTP) |
All Poppify tools: register, start_session_from_photos, apply_session_patch, customize, set_audio, generate_image, confirm, get_result, etc. |
/poppify:make-reel slash command |
Guided session flow — photo-led or topic-led entry, free customize loop, paid confirm. |
/poppify:troubleshoot slash command |
Symptom triage when a render came out wrong. |
/poppify:verify-render slash command |
Download + ffprobe + frame-extract verdict on a finished MP4. |
poppify-build-reel skill |
The canonical photo-led / topic-led flow — when to use which tool, where the free vs paid boundaries are. |
poppify-render-debug skill |
Download the finished MP4, run ffprobe, extract frames, surface a verdict. |
poppify-troubleshoot skill |
Decision tree: symptom → root cause → action for missing audio, wrong colors, dropped captions, stuck renders. |
poppify-schema-introspect skill |
How to verify the deployed MCP schema when a parameter looks silently dropped. |
Install
In Claude Code:
/plugin marketplace add Poppify/poppify-claude-plugin
/plugin install poppify@poppify
That's it. After install:
register({ source: "claude" })mints a wallet and returns anapiKey+ asignupBonusUrl(50 free seeds — claim it before paying).- Use the
poppify-build-reelskill (Claude will auto-invoke when you ask it to "make a reel") to drive the rest.
What does it cost?
- MCP install: free
- All non-generation tools (search library, customize, attach audio, update slides, register, get balance, get topup URL): free
confirmrender: 1 seed basegenerate_image(Gemini): 10 seeds per imagegenerate_music(ElevenLabs Music): 10 seeds per trackgenerate_voiceover(ElevenLabs Voice): 10 seeds per batch
Seeds are sold at $5.99 for 100 seeds (standard pack) or $0.50 for 5 seeds (mini trial pack). 50 seeds are granted free on signup.
Also useful standalone
The reel pipeline is the headline, but every generation primitive is callable on its own — handy for ad-hoc creative tasks, not just full reels:
generate_image— Gemini Imagen, 10 seeds. Workshop the prompt for free first viasuggest_image_prompt, then generate. Returns a URL.generate_music— ElevenLabs Music, 10 seeds. Workshop viasuggest_music_prompt(free), then generate. Returns a URL.generate_voiceover— ElevenLabs Voice, 10 seeds per batch. Browse the curated voice catalog (free) vialist_voices, then generate from a script.search_visual_library/get_music_library— search the existing royalty-free library before generating. FREE. Matches at score ≥ 40 generally beat fresh AI generation.
Generated assets persist to your asset library, so they're reusable across future reels and discoverable on later searches.
Manual install (without the plugin)
If you only want the MCP and don't want the skills:
claude mcp add --transport http poppify https://poppify.ai/mcp
You'll get the same tool surface, but Claude won't have the pre-loaded knowledge about when to call which tool or how to verify the finished video.
Updates
The plugin uses semantic versioning. To get updates:
/plugin marketplace update poppify
Skill content evolves as the MCP surface evolves — we publish new versions when a tool surface changes meaningfully.
Support
- Bug reports / feature requests: file via
submit_feedback({ apiKey, ... })from inside any Claude session — the feedback flows directly to the Poppify team's triage queue. - GitHub Issues: https://github.com/Poppify/poppify-claude-plugin/issues
- Web: https://poppify.ai
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.