Get Uoink

Features / Capture

shipped

Universal page extraction

Save web articles as Markdown and a JSON sidecar on your disk.

Install UoinkBack to features
Captureshipped
Right-click menu on generic webpage showing Uoink action
Right-click menu on generic webpage showing Uoink action
what it does

The user-facing part.

Capture a web article into the same local library as your videos and podcasts. Saved text can be searched and handed to your AI as source material.

getting started

Run the loop.

  1. Open an article or documentation page in your browser.
  2. Right-click the page background.
  3. Click Uoink this page to run the extraction.
  4. Approve the allowlist prompt if this is a new domain.
  5. Check your library for the clean markdown document.
behind the scenes

How Uoink handles it.

The HTTP registry tool uoink_page captures an allowed page, using local Crawl4AI when available and a static HTML fallback otherwise.

mcp reference

Agent-readable surface.

uoink_pagelist_allowed_sitesadd_allowed_site

Full server metadata lives at /mcp and /mcp/manifest.json.

try it now

Run it on your next source.

Add websites to your allowlist and capture articles as clean local markdown.

Install Uoink