{"id":"eddiesanjuan-markupr","name":"markupr","af_score":57.5,"security_score":32.8,"reliability_score":41.2,"what_it_does":"markupR is a local-first desktop capture tool that records screen + optionally voice/narration, aligns the transcript with captured timestamps, extracts relevant frames, enriches the report with context (cursor/app/window/focus hints when available), and outputs structured Markdown (including inline screenshots) for AI coding agents. It also provides a CLI for processing existing recordings and an MCP server for agent-driven capture/analysis workflows.","best_when":"You want local screen/voice capture and then want structured Markdown with screenshots/timestamp alignment for an AI coding agent to act on quickly.","avoid_when":"You need a pure web SaaS API with documented REST/GraphQL contracts, or you cannot install/run local binaries (Electron app/Node CLI/ffmpeg/whisper-node).","last_evaluated":"2026-03-30T15:40:47.466317+00:00","has_mcp":true,"has_api":false,"auth_methods":["No explicit authentication described for MCP/CLI (runs locally via npx/CLI)"],"has_free_tier":false,"known_gotchas":["MCP tools may depend on OS permissions for screen/mic capture and may fail if permissions are denied (not explicitly documented in provided content).","Quality depends on availability of ffmpeg and Whisper model; pipeline degrades gracefully but results may be reduced (transcript-only / timer-based screenshots).","Interactive recording sessions (start_recording/stop_recording) are stateful; agents should avoid interrupting sessions unexpectedly."],"error_quality":0.0}