Substack article extraction

Extract clean markdown texts and metadata from Substack newsletters.

Install Uoink Back to features

Capturein flight

Substack article source with clean markdown body

what it does

The user-facing part.

Extract structured texts from Substack posts. Uoink strips ads, menus, and subscription prompts, saving clean markdown on disk. It preserves external links and layout. The files share the same format as your video corpus and save to your local library automatically.

getting started

Run the loop.

Open a Substack article in your browser.
Right-click the page background.
Select Uoink this article from the context menu.
Approve the domain allowlist prompt.
Check your library for the clean markdown document.

behind the scenes

How Uoink handles it.

The local helper uses a standard extraction path to parse the Substack HTML content. It isolates the article body, filters out marketing widgets, and converts elements to clean markdown syntax. The helper indexes the text in your local database, making it available for local search. Everything runs on your machine.

mcp reference

Agent-readable surface.

uoink_page

{
  "name": "uoink_page",
  "arguments": {
    "url": "https://example.substack.com/p/article-slug"
  }
}

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

try it now

Run it on your next source.

Extract Substack posts as clean local markdown documents.

Install Uoink