• METADATA
  • LINGUISTICS
  • CURATION
  • HUMAN

How to build literary datasets with your AI

Connect Project Gutenberg to your AI client to turn public domain books into structured data for research.

Ask AI about this page

Short answer

How can I use my AI to make book datasets?

Your AI uses the Project Gutenberg MCP to find specific books and pull their metadata, such as author, language, and publication info. This turns a massive library into a clean, structured source for your research.

Dataset outcomes

Where your data lands

The specific outputs your AI generates from the library.

METADATA

Structured book lists

The AI gathers titles, authors, and dates into a format you can use immediately. You get a clean list instead of a pile of raw text.

LINGUISTICS

Language profiles

Your agent identifies the primary languages used in specific collections. This helps you filter datasets by linguistic characteristics.

CURATION

Targeted collections

The AI finds books that fit your exact research criteria. You move from a general search to a specific subset of literature.

HUMAN

Manual verification

You review the final dataset to ensure the metadata matches your research needs. The AI handles the heavy lifting, but you make the final call on quality.

The workflow

What your AI does when the request arrives.

The AI moves from a broad search to specific data extraction.

  1. Find books

    The AI searches the Project Gutenberg library based on your keywords, authors, or genres.

    search_gutenberg_books

  2. Extract details

    Once it finds the right titles, the AI pulls specific metadata for each book.

    get_book_details

  3. Structure data

    The AI organizes the gathered information into a table or a list that fits your research format.

    get_book_details

  4. Filter results

    The AI narrows down the list to only include books that meet your specific language or era requirements.

    search_gutenberg_books

Try it

Copy these to start.

Use these prompts to kick off your data collection.

Starting points

Swap out the bracketed terms for your specific research interests.

Project Gutenberg Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_0UktRYYvxXRVxECo3RB57XwgWKF70ROrXUkcrxsH/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Project Gutenberg capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "project-gutenberg-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_0UktRYYvxXRVxECo3RB57XwgWKF70ROrXUkcrxsH/mcp"
    }
  }
}
Copy into chat04

  • Find 20 books by Charles Dickens and give me a list of their titles and publication years.

  • Search for French language books in the Project Gutenberg collection and list their authors.

  • Get the details for the book 'Moby Dick' and format the metadata into a JSON object.

  • Find all 19th century novels in the library and create a table with title, author, and language.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Project Gutenberg once, then ask.

One click connects the MCP to your client. Your credentials stay encrypted, and you can start querying the library immediately.

Connect Project Gutenberg to your AI

FAQ

How this task behaves

  • 01

    Can the AI download the full text of the books?

    No. The AI can only access metadata and book details through the available tools.

  • 02

    Can the AI edit the books in Project Gutenberg?

    No. The AI can only read information from the library; it cannot change any files or records.

  • 03

    How does the AI find specific authors?

    It uses the search tool to match your author name against the Project Gutenberg database.

  • 04

    Can the AI create a CSV file for me?

    The AI can format the data as a CSV-style list in the chat, but it cannot write a physical file to your hard drive.

  • 05

    Does the AI know if a book is in the public domain?

    Yes, it retrieves the metadata provided by Project Gutenberg, which includes the status of the works.

  • More questions about Project Gutenberg? See everything the Project Gutenberg Connector can do

Connect Project Gutenberg to Claude, Cursor, ChatGPT & more