Skip to content
ToolCargo

A practical MCP workflow

Find books and compare editions with MCP

Search using the title and author, inspect candidate work IDs, and list editions of the chosen work. Read a specific edition record and preserve its source ID, date, publisher and language when supplied. Keep work-level and edition-level metadata separate; a catalogue listing does not establish availability or permission to read a book.

Built for: Readers, librarians and research agents choosing or citing a particular book edition.

What to connect

Create a ToolCargo account and use OAuth or an API key with a supported MCP client. Hosted connectors share your plan’s call quota; connect each required MCP endpoint separately. Review provider permissions before starting.

Client setup and test status · Current plans and limits

Run the workflow

  1. 1. Start with a human research question

    Ask for the title, author and edition requirements. Use ol_search_books with title and author filters or a short plain query. Search relevance and matching titles are candidate signals; review exact work IDs and author names before choosing.

  2. 2. Inspect the work identity

    Call ol_work_details with the returned workId. Record the canonical source, title, linked author IDs and available catalogue metadata. A work groups editions and is not a specific published copy; first-publication metadata and an edition date describe different things.

  3. 3. Compare explicit edition pages

    Use ol_work_editions with the selected workId. Keep limit unchanged when requesting nextOffset; each call reads one bounded page. Choose an editionId and call ol_edition_details. Verify the selected workId is among its linked works and compare publishers, languages, date and identifiers.

  4. 4. Preserve the source and gaps

    Record source URLs, fetchedAt and cacheHit with the shortlist. Missing values remain unknown; malformed or truncated fields need source review. Catalogue records may be revised and projected metadata can be cached for five minutes. Follow the original record before citation or choosing a physical edition.

A prompt to try

Find Pride and Prejudice by Jane Austen in Open Library. Inspect candidate work records, select the correct work, list a page of editions and inspect one linked edition. Report the work ID, edition ID, publication date, publisher, languages and identifiers when supplied. Explain missing metadata and do not infer availability, reading rights or full-text access.

What a useful result looks like

Work ID and title → selected edition ID → catalogue date, publisher and language → declared identifiers → exact source URLs → fetchedAt/cacheHit → missing data and source checks. Keep every supplied value tied to the exact record and do not fill gaps from a different edition.

Know the limits

Human-directed, bounded catalogue discovery. No bulk metadata harvesting, full text, descriptions, covers, borrowing, downloads, availability check or provider account access. Open Library is a community catalogue with incomplete and mutable records. Catalogue presence does not establish ownership, usage rights or reading access; ISBN presence alone is not independent identifier verification.

Common questions

Is a work the same as an edition?

No. A work groups related editions. An edition describes a particular publication and can carry its own publisher, date, language and identifiers.

Does this provide the book or confirm I can borrow it?

No. These tools return public catalogue metadata only.

Can I use it to build a bulk catalogue?

No. Open Library asks bulk users to use its data dumps. This connector supports explicit book research requests and bounded pages.

References and tool documentation

Use the provider’s documentation to check the underlying concepts, and ToolCargo’s references for the exact tools, inputs and limits.

Tool references for this workflow

Continue with the tools

View the main connectorSet up your client

Related workflows