Popcraft: Generate video, images & audio from any AI agent

Hi PH — Eric here, co-founder of Popcraft. We built Popcraft as one studio for the best AI video, image and audio models (Seedance 2.5, Google Omni 1.1, Kling 3.0 Omni, Nano Banana Pro, GPT Image 2.5, ElevenLabs…). Then we noticed our own team stopped opening the app: we were briefing Claude and Cursor and wanting the output to just appear. So Popcraft MCP is the whole platform as an MCP server: One endpoint — https://popcraft.ai/api/mcp — OAuth sign-in, no API key, token auto-refresh 27 tools: explore models, upload references, preview cost, generate video/image/audio/3D, upscale Production workflows served live: ask for "a 15-second vertical UGC ad for this product" and the agent follows our recipe (intake → creator identity → storyboard → realism pass → one Seedance clip with native audio) before it generates anything Works in Claude, Claude Code, Cursor, ChatGPT, Codex — anything that speaks MCP What it's good at today: UGC product ads from one photo, YouTube thumbnails with identity lock, 30-second single-take Seedance 2.5 clips, product image sets, voiceover and music. Honest limits: it runs on Popcraft credits (100 free to start; Pro and Max include a daily Seedance 2.0 Fast & Mini allowance), video is the expensive medium so the agent previews cost before it spends, and canvas/character tools are still coming. Which agent would you run it from, and what would you make first? I'm here all day.