--- title: "Google Books Integration" description: "Search and browse books and magazines through the Google Books catalog: look up volume metadata by ISBN, title, or author, run keyword searches, and read public users' bookshelves." url: https://flowrunner.ai/integrations/google-books date_modified: 2026-08-07T17:20:23-07:00 --- # Google Books [Analytics & Data](https://flowrunner.ai/integrations/category/analytics-data) Search and browse books and magazines through the Google Books catalog: look up volume metadata by ISBN, title, or author, run keyword searches, and read public users' bookshelves. [Verified](https://flowrunner.ai/integrations/verified "What does verified mean?") · 5 actions · API key · available [Google Books website](https://books.google.com/) · [Platform Documentation](https://developers.google.com/books) · Capability data verified 2026-08-12 1. A new book reference enters an intake queue 2. Agent resolves the record with Search Volumes using an isbn qualifier 3. Agent reads title, authors, publisher, page count, and cover 4. Agent checks whether the search returned a single confident match 5. Agent confirms the metadata against the intake reference 6. Agent flags any ambiguous or missing match for review 7. An uncertain match waits for a person before it writes to the catalog ## What This Integration Enables The Google Books connector lets agents read the Google Books catalog inside a workflow. Agents fetch full bibliographic details for a volume ID, run keyword searches with title, author, publisher, subject, and ISBN qualifiers, and page through results with sorting, language, and print-type filters. Bookshelf actions read a public user's shelves and the volumes on each. Because the search is read-only, the connector never changes the catalog; it supplies clean metadata, and the surrounding flow decides what to store and when to ask a human. ### Without FlowRunner **Metadata typed by hand**: Someone looks up each book and copies the details into a record **Inconsistent entries**: Titles, authors, and publishers get entered in different formats **No cover or page data**: Records ship without cover images or page counts ### With FlowRunner **Metadata resolved automatically**: The agent looks up each reference and pulls structured details **Consistent, complete records**: Every entry carries the same fields in the same shape **Ambiguity surfaced**: Uncertain matches become exceptions a person confirms before saving ## Use Case Scenarios ### Reading-List Enrichment A team maintains a reading list or library database. When a new title arrives, the agent calls Search Volumes with an `isbn:` qualifier to resolve the exact edition, then appends the title, authors, and page count to the list. Because ISBN search usually returns a single confident match, most records flow through untouched. When the match is uncertain, the agent holds the record for review instead of guessing. ### Catalog Search in an App A product embeds book search. The agent runs Search Volumes with pagination, sorting, and print-type filters to power the results, then calls Get Volume for full detail when a user selects a title. The connector's qualifiers let the agent narrow by author or subject without building its own search index. ### Personal Library Entry When someone shares a book in chat, the agent calls Search Volumes to find the top match and replies with the author, publisher, and cover thumbnail. If the person confirms, the agent calls Get Volume and writes a richly populated entry into a personal library database. The write only happens after the human confirms the match is right. ## Human-in-Loop Highlight Reading the catalog is safe. Writing an unverified record into your database is where a bad match quietly becomes a bad entry. The connector is read-only, so the agent can search all it wants, but the moment a lookup would create or update a catalog record on an uncertain match, it stops. When Search Volumes returns several plausible editions rather than one, the agent assembles the candidates and routes to the librarian through their channel: "Three editions match this title and author, with different publishers and page counts. Which one should I save, or should I skip it?" This is [human-in-the-loop](https://flowrunner.ai/concepts/human-in-the-loop) at the seam where reference data becomes a record of record: the agent handles the lookup, and a person owns which version is true. Agent processes routinely Detects exception requiring judgment Clear match Continues automatically Ambiguous Routes to human via preferred channel Human decides Agent resumes with decision ## Agent Capabilities 5 actions ### Volumes 2 - **Get Volume** Fetch full bibliographic details for a single volume ID. - **Search Volumes** Run a keyword search with title, author, publisher, subject, and ISBN qualifiers, plus paging and sorting. Use it to resolve a title or power catalog search. ### Bookshelves 3 - **Get Public Bookshelf** Retrieve a single public bookshelf for a Google user. - **List Bookshelf Volumes** List the volumes on a public bookshelf. - **List Public Bookshelves** Browse a Google user's public bookshelves. ## Frequently Asked Questions ### What can FlowRunner do with Google Books? FlowRunner agents can run Search Volumes, Get Volume, and List Public Bookshelves in Google Books, plus 2 more actions. ### Does connecting Google Books to FlowRunner require OAuth? No. Google Books connects to FlowRunner with an API key, no OAuth flow required. ### Can Google Books trigger a FlowRunner workflow automatically? Google Books doesn't currently expose triggers in FlowRunner. It connects as an action step inside workflows started by another trigger. **Work at Google Books?** This integration exposes Google Books to AI agents on every FlowRunner plan, including through MCP, at no cost to you. [See what FlowRunner offers integration partners](https://flowrunner.ai/integrations/partners), including how to keep this page current. --- Markdown version of https://flowrunner.ai/integrations/google-books. Site index: https://flowrunner.ai/llms.txt