MCP server exposing 4 tools for google-books.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/google-books/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}search — FULL-TEXT search inside the actual scanned/printed content of ~40M books via Google Books — find an exact phrase, name, or passage buried inside a book's text, not just its metadata. Use for "search full text for the exact phrase X", "which book mentions Y", historical-record and genealogy lookups (a name + place + date appearing in an old book), or quote verification. Also does plain book/metadata lookup — "find books about X", "books by author Y", verifying ISBNs, finding publishers, getting cover images — pulling structured metadata an LLM would otherwise have to hallucinate. Returns title, authors, publisher, publish date, description, ISBN, page count, cover thumbnails, language, and (when matched) the snippet of book text containing the search terms. Use search_field scoping: intitle:, inauthor:, inpublisher:, subject:, isbn:, lccn:, oclc:.get_volume — Volume detail (full title, authors, description, categories, page count, links).get_by_isbn — Convenience: look up a volume by ISBN-10 or ISBN-13.list_bookshelf — Fetch the public bookshelves for a Google account (by numeric user_id). Omit shelf to list all public shelves; provide a numeric shelf id to list the volumes on that specific shelf.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/google-books/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io