eddiesanjuan/markupr
Give your AI coding agent eyes and ears. Screen + voice capture → structured Markdown. MCP server, CLI, and macOS app.
Combines timestamp-aligned transcription (via Whisper) with frame extraction to map voice narration directly to video moments, then enriches screenshots with cursor position and active window metadata—all processed locally without cloud dependency. Exposes this pipeline across desktop app, CLI, and MCP server interfaces, enabling both synchronous agent-in-conversation capture and asynchronous video-to-Markdown workflows for CI/CD or post-hoc analysis. The structured Markdown output includes inline frames, focus context, and metadata hints designed specifically for LLM consumption rather than generic image dumps.
Available on npm.
Stars
9
Forks
1
Language
TypeScript
License
MIT
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Dependencies
12
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/eddiesanjuan/markupr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yeominux/md-feedback
Browser-first markdown plan review. Start local web review in one command, then let your agent...
MoussaabBadla/code-screenshot-mcp
MCP server for generating beautiful code screenshots directly from Claude
kmoulder/screen-capture-mcp
MCP server that gives Claude Code the ability to take screenshots (Windows)
sethbang/mcp-screenshot-server
An MCP server that provides AI assistants with screenshot capabilities — both web page capture...
just-every/mcp-screenshot-website-fast
Quickly screenshots webpages and converts to an LLM friendly size