February 15, 2026
Mark the screen. Keep moving. Report every issue.
MarkuprX v3.0.0 lets you hold Command or Control and draw over the live recording without taking normal mouse control away. Each following click saves one marked screen with the narration that explains it.
Your agent still misses intent from raw screenshots.
Even with a transcript and images, agents can misread what you meant: where your pointer was, which window was active, and what element you were referencing are often missing.
That ambiguity creates extra back-and-forth and slower fixes, especially when you're reviewing dense interfaces or multi-window workflows.
Capture context, not just pixels.
v3.0.0 keeps normal pointer interaction intact while adding a temporary live markup layer. Release the modifier, click to save and clear, then continue reviewing the next screen.
This metadata flows through desktop app output, CLI templates, and MCP sessions so your agent sees what changed, where attention was focused, and what to fix next.
Multiple findings in one video remain separate issues, each with its own marked screenshot, timestamp, tools, colors, and matching spoken comment.
What's new in v3.0.0
Live markup that stays out of your way.
Mark screens while reviewing, keep interacting normally, and receive one evidence-backed report item per finding.
### FB-003: Primary CTA disabled state unreadable
The button text almost disappears in dark mode.
Looks like contrast token fallback is wrong.
Capture context: cursor 1186,642 • app "Arc" • window "Settings"
Focus hint: button[aria-label="Retest"]All interfaces still use one pipeline: Capture → Transcribe → Align → Enrich → Generate. Comprehensive automated coverage across the suite.
Four interfaces, one pipeline
Use it however you work.
Desktop App
Menu bar → ⌘⇧FLives in your macOS menu bar. Hit the hotkey, narrate what you see, stop, paste. Full GUI with session history and annotation tools.
CLI
npx markuprx analyze ./recording.movSame pipeline, no desktop app required. Watch mode monitors directories. Point it at a video or let it process recordings as they appear.
MCP Server
npx --package markuprx markuprx-mcpYour AI agent triggers captures mid-conversation. No copy-paste, no context switching. The agent asks to see your screen, MarkuprX delivers the report.
GitHub Action
eddiesanjuan/markuprx-action@v1Add visual feedback to every PR in CI/CD. The action processes recordings and posts structured reports as PR comments automatically.
Under the hood
The pipeline.
Every interface -- desktop, CLI, MCP, GitHub Action -- runs the same core pipeline. Capture → Transcribe → Align → Enrich → Generate.
- Context-aware capture snapshots Shot events now include cursor coordinates, active app/window hints, and focused-element context (best effort) for clearer agent interpretation.
- Desktop + MCP parity Context metadata now flows through desktop output, MCP session metadata, and generated templates so every interface tells the same story.
- Template-aware report output Structured Markdown and JSON outputs now carry capture context near relevant frames to reduce follow-up clarification.
- BYOK reliability polish Dark mode readability and key-readiness sync were tightened so onboarding and advanced settings stay clear and accurate.
- Comprehensive automated coverage, MIT licensed No telemetry. No tracking. No analytics. Open source with comprehensive test coverage across the full pipeline.
Get started