For Developers & AI

Search, read, and cite rare historical texts via MCP, CLI, or REST. No API key needed.

Request an API Key

For bulk access to OCR text, translations, and page-level data. Keys are reviewed within 24 hours.

What you can build

A researcher studying Renaissance natural philosophy wants to trace how the concept of “spiritus mundi” evolves from Ficino through Agrippa to Fludd. With the MCP server connected to Claude, they search across all three authors' translated works in a single conversation, pull exact passages with page citations, and compile a comparative analysis with DOI-backed references — work that would take days in a physical archive.

The same tools work for building research apps, enriching datasets with primary source references, or giving AI systems grounded access to pre-modern texts that aren't in their training data.

MCP Server

Gives Claude (and any MCP client) direct access to the full collection — search, read, quote, and browse 50,000+ illustrations. One command to install.

Claude Code
claude mcp add source-library -- npx -y @source-library/mcp-server
Claude DesktopmacOS: ~/Library/Application Support/Claude/  •  Windows: %APPDATA%\Claude\
{
  "mcpServers": {
    "source-library": {
      "command": "npx",
      "args": ["-y", "@source-library/mcp-server"]
    }
  }
}

Tools

search_libraryFull-text search across books and page content
search_translationsSearch inside translated text across the whole library
search_within_bookSearch inside a specific book's pages
list_booksBrowse with filters — language, year, category, translation status
get_bookBook metadata: summary, chapters, edition info, DOI
get_book_textRead 50+ pages in one call — OCR, translation, or both
get_quoteExact text of a single page with citation URL
search_imagesSearch 50,000+ historical illustrations by subject, symbol, type

Try asking Claude

“Search for references to ‘prima materia’ across the collection. Which authors discuss it, and how do their treatments differ?”

“Read the full translation of Fludd's History of Both Worlds, pages 1–50. Summarize the cosmological framework.”

“What does Copernicus say about the Sun's centrality in De Revolutionibus? Find the key passages with citation URLs.”

“Find all alchemical emblems depicting the ouroboros. What texts are they from?”

Command Line

Same tools as the MCP server, but standalone with colored terminal output. Add --json for scripts.

# Install
npm install -g @source-library/mcp-server

# Search the collection
source-library search "Paracelsus" --language=German

# Search inside translations
source-library translations "harmony of the spheres"

# Read a book
source-library text fludd-utriusque --from=1 --to=50

# Get exact text for quoting
source-library quote fludd-utriusque 57

# Browse illustrations
source-library images --subject=alchemy --type=emblem

# JSON output for piping
source-library search "alchemy" --json | jq .results

REST API

Direct HTTP access, no authentication. The MCP server and CLI use these same endpoints.

Base URL: https://sourcelibrary.org/api
GET/search

Full-text search across books and page content

qstringSearch query (required)
languagestringFilter by language
year_from / year_tonumberPublication year range
sortstringrelevance, date_asc, date_desc, title
GET /search?q=philosopher's stone&language=Latin
GET/books/:id/text

Get full book text (OCR, translation, or both) in a single call

contentstringocr, translation, or both (default)
from / tonumberPage range (inclusive)
formatstringjson (structured) or plain (concatenated text)
GET /books/fludd-utriusque/text?content=translation&from=1&to=50
GET/books/:idBook metadata, summary, DOI
GET/books/libraryBrowse with language/category/collection filters
GET/books/:id/searchSearch within a book's pages
GET/books/:id/quoteSingle-page text for verbatim quoting
GET/gallerySearch 50,000+ historical illustrations
GET/catalog/csvDownload the full catalog as CSV

Dataset API

For bulk access to OCR text, translations, and page-level data, request an API key. Keys are reviewed within 24 hours.

Request an API Key

Citation URLs

Every page includes a citation URL linking directly to the source. Published editions have DOIs via Zenodo.

Page

https://sourcelibrary.org/book/fludd-utriusque?page=57

Book

https://sourcelibrary.org/book/fludd-utriusque

With DOI

Author, Title, trans. Source Library (Year), p. N. DOI: 10.5281/zenodo.xxxxx

/llms.txt

Complete API documentation formatted for LLM consumption.

Pipeline Architecture

How books flow through 10 processing stages: Lambda workers, SQS queues, Gemini AI, backpressure controls. Live counts, diagrams, cost breakdowns.

This library is built in the open.

If you spot an error, have a suggestion, or just want to say hello — we’d love to hear from you.