ViralRecast
Shows what is going viral, why it worked, and cuts the clips for you.
01The problem
Creators and marketers lose hours scrolling to find what is working, and then still have to guess why it worked.
02What I built
Finds what is going viral on TikTok, Reels and YouTube, explains the anatomy of each post (hook, emotion, replay peaks) and cuts the vertical clips with captions. It also reads the ad libraries, so you see what competitors pay to promote. A web dashboard for people, and an MCP server so the same product runs inside Claude and ChatGPT.
03The decision that mattered
One product, two doors, one wallet. People use the dashboard, agents use MCP, and both spend from the same atomic credit wallet that refunds a job when it fails. The balance a user sees is always the balance they have.
04Receipts
- MCP server with OAuth 2.1, PKCE and dynamic client registration, or a personal key for Claude Code and Cursor
- Postgres 16 with pgvector and an HNSW index for post similarity
- Atomic credit wallet with automatic refund of failed jobs, billing on Stripe
- Media engine is Renderster, my own video rendering service
05MCP
Social and ad intelligence: read any post, find what is viral, read competitor ads, transcribe and cut clips. · OAuth 2.1 + PKCE + DCR, or personal key
read_postsearch_viral_contenttrending_nowsimilar_contentanalyze_creatorsearch_adsadvertiser_adsread_adtranscribe_videodownload_videocreate_clipsget_jobmy_historyget_account