Connect Claude

“I’ll have it sent up.” Two copy-pastes and your Claude can see the library — list books, check reading progress, read pages, start jobs, pull clean markdown. The commands below are complete; your token is already filled in.

Copy your token

This is your login — treat it like a password.

eyJ1aWQiOjI1M30.yxOshHtOdBR28DehzOIQuGEWFyA

Paste this into your terminal

One command — the app itself speaks MCP over HTTP, nothing to download.

claude mcp add --transport http owlscan https://owlacade.my/mcp \
  --header "Authorization: Bearer eyJ1aWQiOjI1M30.yxOshHtOdBR28DehzOIQuGEWFyA"

Claude Desktop / claude.ai instead: Settings → Connectors → Add custom connector → URL https://owlacade.my/mcp with that same Bearer token. No terminal at all.

Just ask

Open Claude and talk about your books like a colleague would:

“What’s the reading status of The Supernatural Virtues?”
“Read me page 12 and fix the footnotes.”
“Export the book as clean markdown and tidy the chapter headings.”

Prefer the local bridge script?

The stdio bridge runs on your machine and proxies the same API. Optional: add -e GEMINI_API_KEY=your-key to run reading jobs on your own key (free at aistudio.google.com/apikey) — it rides each request in memory and is never stored.

curl -fsSL https://owlacade.my/scandoc_mcp.py -o ~/.scandoc_mcp.py

claude mcp add owlscan \
  -e SCANDOC_URL=https://owlacade.my \
  -e SCANDOC_TOKEN=eyJ1aWQiOjI1M30.yxOshHtOdBR28DehzOIQuGEWFyA \
  -- python3 ~/.scandoc_mcp.py

No MCP? Just take the files

The whole library is plain HTTP — Claude (or anything) can fetch it directly. Paste a URL into any session and ask it to transcribe.

https://owlacade.my/api/books                 # your library
https://owlacade.my/books/<id>/scan.pdf       # raw scan PDF (?enhanced=1 for cleaned)
https://owlacade.my/books/<id>/clean.md       # stitched clean-markdown transcript
https://owlacade.my/books/<id>/export.md      # per-page OCR text