For Agents
Search Open Library for books and authors, resolve ISBNs and Open Library IDs to bibliographic records, list works by subject, and fetch cover images. No API key required.
Use for: Search for books about climate change, Find all works written by a given author, Look up a book by its ISBN, Get the details of a work by its Open Library ID
Not supported: Does not handle ebook lending, user reading logs, or book purchases. Use for book, author, and bibliographic data lookup only.
The Open Library API looks up books, works, authors, subjects, and cover images from the Open Library collection by identifier or free-text search. It resolves an ISBN or Open Library ID to a full bibliographic record, returns an author profile and the works attributed to them, lists the works filed under a subject, and serves cover artwork at several sizes. Search endpoints return ranked matches for book titles and author names as JSON.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Open Library API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fopenlibrary.org%2Fopenlibrary" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fopenlibrary.org%2Fopenlibrary" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Open Library API.
Search the book collection by title, author, or keyword
Search for authors by name and read their attributed works
Resolve an ISBN to a full book record
Fetch a book edition, work, or author by its Open Library ID
List the works filed under a given subject
Retrieve cover artwork for a book at small, medium, or large size
Patterns agents use Open Library API for, with concrete tasks.
★ AI Agent Book Lookup
An AI agent building a reading list or enriching a citation can resolve a title or ISBN to a complete bibliographic record through Jentic. The agent searches by intent, passes the identifier or query, and receives the matching book, work, or author record without the developer reading the Open Library reference docs or handling any key, since the API is public.
Call GET /isbn/9780140328721 to resolve the ISBN to its Open Library edition record
Collection Search and Discovery
Reading apps and recommendation tools let users find books by title, author, or keyword. The search endpoint returns ranked matches with their Open Library IDs, which the app then expands into full edition and work records to display covers, descriptions, and publication details.
Call GET /search.json with a title query, then read the matching work IDs from the results
Author and Subject Browsing
Library catalogs and literary sites build author pages and subject shelves. The author endpoint returns a profile, the author-works endpoint lists their titles, and the subject endpoint returns the works filed under a topic, so an agent can assemble a browsable collection around any author or theme.
Call GET /authors/OL23919A/works.json to list the works attributed to that author
11 endpoints — the open library api looks up books, works, authors, subjects, and cover images from the open library collection by identifier or free-text search.
METHOD
PATH
DESCRIPTION
/search.json
Search books by title, author, or keyword
/search/authors.json
Search for authors by name
/isbn/{isbn}
Resolve an ISBN to a book edition
/books/{olid}
Get a book edition by Open Library ID
/works/{olid}
Get a work by Open Library ID
/authors/{olid}.json
Get an author by Open Library ID
/subjects/{subject}.json
List works filed under a subject
/covers/{key_type}/{value}-{size}.jpg
Get a cover image at a given size
/search.json
Search books by title, author, or keyword
/search/authors.json
Search for authors by name
/isbn/{isbn}
Resolve an ISBN to a book edition
/books/{olid}
Get a book edition by Open Library ID
/works/{olid}
Get a work by Open Library ID
/authors/{olid}.json
Get an author by Open Library ID
/subjects/{subject}.json
List works filed under a subject
/covers/{key_type}/{value}-{size}.jpg
Get a cover image at a given size
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>What agents get from Jentic-routed access to this vendor.
Setup
The Open Library API needs no API key, so there is nothing to wire up before your agent can call it. Through Jentic you install once, import Open Library from the API Directory, and your agent searches books and reads records straight away.
Permission scoping
This API is read-only, so a rule can bound your agent to the lookups it needs, such as book search and ISBN resolution, and exclude the rest. You choose the operation set, so the agent can read bibliographic data but cannot reach anything you did not grant.
Credential isolation
Open Library needs no API key or token, so there is no secret to store or inject. Jentic still runs every call from your own self-hosted instance, so execution stays on your infrastructure.
Intent-based discovery
Agents search Jentic by intent such as 'look up a book by ISBN' or 'search for an author', and Jentic returns the matching Open Library operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Open Library API through Jentic.
What authentication does the Open Library API use?
The Open Library API requires no authentication; its endpoints are public per the OpenAPI spec. Through Jentic the calls still run from your own self-hosted instance, so you keep an audit log of everything the agent requests.
Can I resolve an ISBN to book data with the Open Library API?
Yes. The ISBN endpoint returns the matching edition record, and you can follow its work and author IDs to pull the full bibliographic detail. Free-text search is available when you only have a title or author name.
What are the rate limits for the Open Library API?
The OpenAPI spec does not specify rate limits. Open Library asks clients to call the API responsibly and documents current guidance at https://openlibrary.org/developers/api.
How do I search Open Library through Jentic?
Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then import Open Library from the API Directory. Your agent searches for an intent such as 'search books by title', and Jentic returns the matching operation with its input schema. There is no key to configure. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there an Open Library MCP server?
You do not need an MCP server to give your agent the Open Library API. Jentic connects it directly from the API Directory: import the API and your agent calls the search and lookup operations on demand, which keeps your agent's context free of an extra server's tool definitions.
Can I limit what my agent is allowed to do with the Open Library API?
Yes. Every operation is a read, so you can allow only the ones the agent needs, such as book search and ISBN lookup, while leaving out author or subject browsing. Because you run Jentic One yourself, the agent holds no access beyond the read operations you grant, and every call is logged.
GET STARTED