InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Extract text, Markdown and metadata from PDF URLs or uploads via Apify, per document or per page.

    Stale Official MCP Registry, com.ctriolab Updated 7 days ago 1 note

  2. Inkpluck: read web articles as Markdown + title, authors, date, language (newspaper3k successor)

    Stale Official MCP Registry, dev.workers.cybermax-tools.cybermax Updated 38 days ago 1 note

  3. x402 clean article text and metadata for AI/RAG. $0.002 per successful article.

    Stale Official MCP Registry, io.github.industrial-platform-ai Updated 48 days ago 1 note

  4. x402 PDF text, pages, and metadata for AI/RAG. $0.0015 per successful PDF.

    Stale Official MCP Registry, io.github.industrial-platform-ai Updated 48 days ago 1 note

  5. 16 BEM naming rules read the HTML file you have open and 22 markup and SCSS skeletons write the styl

    Stale Official MCP Registry, io.github.jmshinhwa Updated 59 days ago 1 note

    @readystack/bem-class-extractor-html@0.1.2
  6. Turn any URL into clean Markdown or text for LLMs, RAG and agents. Strips nav, ads and footers.

    Stale Official MCP Registry, io.github.kitedesk-erm Updated 25 days ago 2 notes

    @kitedesk-erm/url-to-markdown-mcp@1.0.0
  7. Extract the main text, title, publish date, language and lead image of articles

    Stale Official MCP Registry, io.github.kriton-dev Updated 15 days ago 1 note

  8. Find declared favicons, touch icons, manifest links and theme colors on public website pages.

    Stale Official MCP Registry, io.github.kriton-dev Updated 15 days ago 1 note

  9. Pull every link a sitemap holds for SEO audits, migrations and crawl planning.

    Stale Official MCP Registry, io.github.bepolabs Updated 5 days ago 1 note

  10. Convert noisy HTML into clean Markdown, JSON tables & JSON-LD with token metrics via x402 USDC.

    Indexed Official MCP Registry, io.github.brunopompeo1 Updated yesterday 1 note

  11. Scrape any company's Lever job board and get clean, de-duplicated job data: title, team, location…

    Stale Official MCP Registry, com.ranovam Updated 50 days ago 1 note

  12. PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.

    Stale Official MCP Registry, io.github.bkeller-research Updated 41 days ago 1 note

  13. Every URL in a site's sitemaps, with lastmod. Runs on Apify, $0.30 per 1,000 URLs.

    Stale Official MCP Registry, io.github.jordan-belfort-ai Updated 36 days ago 1 note

  14. Extract text, tables and RAG chunks from public PDF URLs; pay-per-event via your Apify account.

    Stale Official MCP Registry, io.github.truhojunbot-tech Updated 40 days ago 1 note

  15. Full text, author, date and image for every news or blog link in a dataset, CSV or Google Sheet.

    Stale Official MCP Registry, io.github.Nero-Engine Updated 31 days ago 1 note

  16. Apify actor via Apify's MCP server (Apify token needed): frames from video file URLs.

    Stale Official MCP Registry, dev.pages.video-frames-to-images Updated 11 days ago 1 note

  17. ffprobe metadata, frames, scene cuts, contact sheet and loudness from direct video or audio links.

    Stale Official MCP Registry, io.github.faithdrivencreator Updated 8 days ago 1 note

  18. Extract the URLs listed in a website's sitemaps, following indexes, gzip and RSS sitemaps

    Stale Official MCP Registry, io.github.kriton-dev Updated 15 days ago 1 note

  19. Pay-per-call web page summarizer: $0.01 via x402 (USD₮0, X Layer). Free sampling available.

    Stale Official MCP Registry, io.github.SuBai520-QWQ Updated 7 days ago 1 note

  20. Turn PDF links or uploaded files into Markdown and plain text, one row per page.

    Stale Official MCP Registry, io.github.bepolabs Updated 5 days ago 1 note

  21. Published emails, phones and social profiles for every website in a list, CSV or Google Sheet.

    Stale Official MCP Registry, io.github.Nero-Engine Updated 2 months ago 1 note

  22. Read printed words from receipts, forms and book pages, then export them as JSON, CSV or Excel.

    Stale Official MCP Registry, io.github.bepolabs Updated 5 days ago 1 note

  23. Titles, meta descriptions, canonical, Open Graph and Twitter tags of many pages, with an SEO score.

    Stale Official MCP Registry, dev.workers.cybermax-tools.cybermax Updated 19 days ago 1 note

  24. Extract text, tables and metadata from every PDF linked in a dataset, CSV or Google Sheet.

    Stale Official MCP Registry, io.github.Nero-Engine Updated 2 months ago 1 note

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.