mcp-open-library
This MCP server provides read-only Open Library lookups for books and authors.
Search the catalogue with
search_booksby free-form query, title, author, subject, place, person, publisher, or ISBN, with language filtering, sorting, and paging.Find books by title with
get_book_by_title.Find authors by name with
get_authors_by_name.Retrieve detailed author records with
get_author_infousing an Open Library author key.Get author photo URLs with
get_author_photo, or a message when no photo exists.Get book cover URLs with
get_book_coverby ISBN, OCLC, LCCN, OLID, or cover ID, with selectable size.Retrieve detailed book/edition data with
get_book_by_idusing ISBN, LCCN, OCLC, or OLID.Use search result
best_edition.edition_keywithget_book_by_idto move from a work to a concrete edition.All tools are read-only and report failures as tool errors for correction.
Referenced in the repository URL for cloning the project.
Used for package management and running scripts.
Used for code formatting in the development workflow.
Used as the implementation language for the MCP server.
Used for comprehensive test coverage of the MCP server.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-open-library find information about The Great Gatsby"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Open Library
![]()
A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book and author information.
Overview
This project implements an MCP server that provides tools for AI assistants to interact with the Open Library. It allows searching the catalogue by title, author, subject and other fields, searching for authors by name, retrieving detailed author information using their Open Library key, and getting URLs for book covers and author photos. The server returns JSON projections of the Open Library responses rather than the raw payloads.
Related MCP server: bookstore-mcp-server
Features
Book Search: Search across titles, authors, subjects, places, people, publishers and ISBNs, with sorting and paging (
search_books).Book Search by Title: Search for books using their title (
get_book_by_title).Author Search by Name: Search for authors using their name, with paging (
get_authors_by_name).Get Author Details: Retrieve detailed information for a specific author using their Open Library key (
get_author_info).Get Author Photo: Get the URL for an author's photo using their Open Library ID (OLID) (
get_author_photo).Get Book Cover: Get the URL for a book's cover image using various identifiers (ISBN, OCLC, LCCN, OLID, ID) (
get_book_cover).Get Book by ID: Retrieve detailed book information using various identifiers (ISBN, LCCN, OCLC, OLID) (
get_book_by_id).
Search results are paged — every search tool returns at most limit results (default 10, maximum 50) alongside num_found, the total number of matches, which you page through with offset (maximum 1000). The two cover tools check that an image actually exists and say so when it does not, rather than handing back a URL that resolves to a blank placeholder.
Every tool is a read-only lookup and advertises itself as such with the readOnlyHint and openWorldHint annotations, which may allow a client to skip the confirmation prompt it shows for tools that could change something. These are hints: the MCP specification has clients treat annotations as untrusted unless the server is trusted, so the confirmation policy is the client's to decide. Failures — an unreachable API, a rejected argument — come back as a tool result flagged isError, so an assistant can read what went wrong and correct its next call rather than the request failing outright.
Installation
Quick Start
Nothing to install or build. Point an MCP client at the package with npx and it
will be fetched on first run:
{
"mcpServers": {
"mcp-open-library": {
"command": "npx",
"args": ["-y", "mcp-open-library"]
}
}
}In Claude Desktop that goes in claude_desktop_config.json; other clients use the
same shape. Restart the client and the seven tools below become available.
MCP Registry
This server publishes to the official MCP Registry as
io.github.8enSmith/mcp-open-library from v1.0.3 onwards. Clients that
support the registry can install it by that name.
To inspect the published listing:
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.8enSmith/mcp-open-library"Manual Installation
# Clone the repository
git clone https://github.com/8enSmith/mcp-open-library.git
cd mcp-open-library
# Install dependencies
npm install
# Build the project
npm run buildUsage
Running the Server
Ensure you are running node v22.23.4 (it'll probably work on a newer version of node but this is what Im using for this test). If you have
nvminstalled runnvm use.In the
mcp-open-libraryroot directory runnpm run buildNext run
npm run inspector. Once built, click the URL with theMCP_PROXY_AUTH_TOKENquery string parameter to open the Inspector.In the Inspector, choose 'STDIO' transport
Make sure the command is set to 'build/index.js'
Click the 'Connect' button in the Inspector - you'll now connect to the server
Click 'Tools' in the top right menu bar
Try running a tool e.g. click get_book_by_title
Search for a book e.g. In the title box enter 'The Hobbit' and then click 'Run Tool'. Server will then return book details.
Using with an MCP Client
This server implements the Model Context Protocol, which means it can be used by any MCP-compatible AI assistant or client e.g. Claude Desktop. The server exposes the following tools:
search_books: Search the catalogue by any combination of query, title, author, subject, place, person, publisher and ISBNget_book_by_title: Search for book information by titleget_authors_by_name: Search for author information by nameget_author_info: Get detailed information for a specific author using their Open Library Author Keyget_author_photo: Get the URL for an author's photo using their Open Library Author ID (OLID)get_book_cover: Get the URL for a book's cover image using a specific identifier (ISBN, OCLC, LCCN, OLID, or ID)get_book_by_id: Get detailed book information using a specific identifier (ISBN, LCCN, OCLC, or OLID)
Example search_books input:
{
"author": "Ursula K. Le Guin",
"subject": "fantasy",
"sort": "old",
"limit": 2
}Example search_books output:
{
"num_found": 51,
"offset": 0,
"limit": 2,
"results": [
{
"title": "A Wizard of Earthsea",
"authors": ["Ursula K. Le Guin"],
"first_publish_year": 1968,
"open_library_work_key": "/works/OL59798W",
"edition_count": 87,
"author_keys": ["OL31353A"],
"best_edition": {
"edition_key": "OL5613890M"
},
"cover_url": "https://covers.openlibrary.org/b/id/13617691-M.jpg",
"ratings_average": 3.95,
"ebook_access": "borrowable"
}
]
}best_edition is one specific edition of the work — the one Open Library ranks best for your query — carrying that edition's own identifiers. Search results otherwise identify a work (open_library_work_key), which no tool accepts, so this is the route from a search hit to a concrete book.
Its edition_key is an OLID you can pass straight to get_book_by_id for the full edition record, including its complete ISBN arrays:
{ "idType": "olid", "idValue": "OL5613890M" }The isbn_13 / isbn_10 fields are omitted where Open Library holds no ISBN for that edition — as in the example above, and roughly a third of results — while edition_key is essentially always present. Where an edition lists several ISBNs of one kind, the first is reported; get_book_by_id returns them all.
The search_books tool accepts the following parameters:
At least one of
q,title,author,subject,place,person,publisherorisbn— the request is rejected without one, since an unfiltered search matches the entire catalogue.qtakes a free-form Solr query such assubject:cyberpunk AND first_publish_year:[1980 TO 1990]language: Optional 3-letter MARC language code (e.g.eng,fre)sort: Optional ordering —new,old,random,key,rating,readinglog,want_to_read,currently_reading,already_readortitle. Omit for relevancelimit: Optional, 1–50, defaults to 10offset: Optional, 0–1000, defaults to 0
Example get_book_by_title input:
{
"title": "The Hobbit",
"limit": 1
}Example get_book_by_title output:
{
"num_found": 224,
"offset": 0,
"limit": 1,
"results": [
{
"title": "The Hobbit",
"authors": ["J.R.R. Tolkien"],
"first_publish_year": 1937,
"open_library_work_key": "/works/OL27482W",
"edition_count": 481,
"author_keys": ["OL26320A"],
"best_edition": {
"edition_key": "OL51709286M",
"isbn_13": "9780395520215",
"isbn_10": "0395520215"
},
"cover_url": "https://covers.openlibrary.org/b/id/14627509-M.jpg",
"ratings_average": 4.29,
"ebook_access": "borrowable"
}
]
}Example get_authors_by_name input:
{
"name": "J. R. R. Tolkien",
"limit": 2
}Example get_authors_by_name output:
Each result's key can be passed to get_author_info for that author's full
record. alternate_names is abridged here.
{
"num_found": 2,
"offset": 0,
"limit": 2,
"results": [
{
"key": "OL26320A",
"name": "J.R.R. Tolkien",
"alternate_names": ["John Ronald Reuel Tolkien", "Tolkien"],
"birth_date": "3 January 1892",
"top_work": "The Hobbit",
"work_count": 355
},
{
"key": "OL332676A",
"name": "J. R. R. Tolkien Centenary Conference (1992 Keble College, Oxford)",
"top_work": "Proceedings of the J.R.R. Tolkien Centenary Conference, 1992",
"work_count": 2
}
]
}Example get_author_info input:
{
"author_key": "OL26320A"
}Example get_author_info output:
{
"name": "J. R. R. Tolkien",
"personal_name": "John Ronald Reuel Tolkien",
"birth_date": "3 January 1892",
"death_date": "2 September 1973",
"bio": "John Ronald Reuel Tolkien (1892-1973) was a major scholar of the English language, specializing in Old and Middle English. He served as the Rawlinson and Bosworth Professor of Anglo-Saxon and later the Merton Professor of English Language and Literature at Oxford University.",
"alternate_names": ["John Ronald Reuel Tolkien"],
"photos": [6791763],
"key": "/authors/OL26320A",
"remote_ids": {
"viaf": "95218067",
"wikidata": "Q892"
},
"revision": 43,
"last_modified": {
"type": "/type/datetime",
"value": "2023-02-12T05:50:22.881"
}
}Example get_author_photo input:
{
"olid": "OL26320A"
}Example get_author_photo output:
https://covers.openlibrary.org/a/olid/OL26320A-L.jpgWhen Open Library has no photo for that author, the tool says so instead of returning a URL:
No author photo available for OLID OL99999999A.Example get_book_cover input:
{
"key": "ISBN",
"value": "9780547928227",
"size": "L"
}Example get_book_cover output:
https://covers.openlibrary.org/b/isbn/9780547928227-L.jpgAs with author photos, a book with no cover produces a message rather than a URL:
No cover image available for OLID OL00000000M.The get_book_cover tool accepts the following parameters:
key: The type of identifier (one of:ISBN,OCLC,LCCN,OLID, orID)value: The value of the identifiersize: Optional cover size (Sfor small,Mfor medium,Lfor large, defaults toL)
Example get_book_by_id input:
{
"idType": "isbn",
"idValue": "9780547928227"
}Example get_book_by_id output:
{
"title": "The Hobbit",
"authors": [
"J. R. R. Tolkien"
],
"publishers": [
"Houghton Mifflin Harcourt"
],
"publish_date": "October 21, 2012",
"number_of_pages": 300,
"isbn_13": [
"9780547928227"
],
"isbn_10": [
"054792822X"
],
"oclc": [
"794607877"
],
"olid": [
"OL25380781M"
],
"open_library_edition_key": "/books/OL25380781M",
"open_library_work_key": "/works/OL45883W",
"cover_url": "https://covers.openlibrary.org/b/id/8231496-M.jpg",
"info_url": "https://openlibrary.org/books/OL25380781M/The_Hobbit",
"preview_url": "https://archive.org/details/hobbit00tolkien"
}The get_book_by_id tool accepts the following parameters:
idType: The type of identifier (one of:isbn,lccn,oclc,olid)idValue: The value of the identifier
An example of this tool being used in Claude Desktop can be see here:
Docker
You can test this MCP server using Docker. To do this first run:
docker build -t mcp-open-library .
docker run -p 8080:8080 mcp-open-libraryYou can then test the server running within Docker via the inspector e.g.
npm run inspector http://localhost:8080Development
Project Structure
src/index.ts- The MCP server: builds the HTTP clients and drives both request handlers from the tool registrysrc/index.test.ts- Tests for the server wiring, including a snapshot of the published tool schemassrc/tools/<tool-name>/- One directory per tool, each containingindex.ts(the handler, its Zod argument schema and itsToolDefinition),index.test.ts, and — for tools with a non-trivial API response — atypes.tsdescribing that response shapesrc/tools/registry.ts- TheTOOLSarray, the single list of what the server exposessrc/tools/types.ts- TheToolDefinitionandToolHandlercontractssrc/utils/- Shared plumbing:http.ts(the API and covers Axios clients),errors.ts(argument parsing and error results),results.ts,schema.ts(Zod → JSON Schema),search.ts(the shared search projection and paging schemas),covers.tsscripts/- Release automation (sync-server-json.mjs,promote-changelog.mjs,assert-release-consistency.mjs) and its tests
A tool's input contract is declared once, as a Zod schema. The JSON Schema that MCP clients
see is generated from it by toInputSchema, so the two cannot drift. Field descriptions come
from .describe() on the Zod schema. Note that .refine() constraints are dropped in
translation — a cross-field rule has to be stated in the tool's description too, or clients
will never learn about it.
Adding a tool means creating the directory and adding one entry to TOOLS in
src/tools/registry.ts. src/index.test.ts derives its expectations from that array, so the
only test change is an updated schema snapshot (npx vitest run -u).
Available Scripts
npm run build- Build the TypeScript codenpm run watch- Watch for changes and rebuildnpm test- Run the test suite in watch modenpm run test:precommit- Run the test suite once and exitnpm run lint/npm run lint:fix- Lintsrcandscriptswith ESLintnpm run format- Format code with Prettiernpm run inspector- Run the MCP Inspector against the server
Running Tests
npm test starts Vitest in watch mode:
npm testFor a single pass — what the pre-commit hook and CI run — use:
npm run test:precommitTo run one file or one test case:
npx vitest run src/tools/get-book-by-id/index.test.ts
npx vitest run -t "should return book details when given a valid OLID"Releasing
Releases are automated. Pushing a v* tag triggers
publish-mcp.yml, which runs the checks, publishes the package
to npm, registers the new version with the MCP Registry, and then creates a GitHub Release using
that version's CHANGELOG.md section as the notes. Both npm and the registry authenticate over
GitHub OIDC, so there are no publishing secrets to manage.
package.json's version is the single source of truth. npm version derives everything else from
it via a version lifecycle hook, so a release is one command:
npm version patch # or minor / major
git push --follow-tagsThat single command bumps package.json, rewrites server.json to match, promotes the changelog's
## [Unreleased] heading to the new version and today's date, and commits the lot under one tag.
Two things to know before you run it:
Write your changelog entries first. They go under a
## [Unreleased]heading inCHANGELOG.mdas you merge work.npm versionfails if that heading is missing, rather than releasing something undocumented. If it does fail, undo the partial bump withgit restore --source=HEAD --staged --worktree package.json package-lock.json server.json.The working tree must be clean, and the pre-commit hook (lint + full test suite) runs inside
npm version.
CI re-asserts that the tag, package.json, server.json and CHANGELOG.md all agree before
anything is published — see scripts/assert-release-consistency.mjs. The same check runs on pull
requests that touch those files.
npm version is not a retry
Once it prints the new tag, the commit and tag exist and the release is done locally — the next step is
git push --follow-tags, not running npm version again. A second run attempts the next
version, and will fail on the missing ## [Unreleased] heading (which the first run consumed). That
failure is safe by design, but it leaves package.json, package-lock.json and server.json
bumped and uncommitted. Undo with:
git restore --source=HEAD --staged --worktree package.json package-lock.json server.jsonIf the publish workflow fails
Re-running the job from the Actions tab only helps for a transient failure. GitHub runs the workflow
as it existed at the tagged commit, so a bug in the workflow itself or in server.json cannot be
fixed by a re-run — the fix has to be in the commit the tag points at.
Nothing is published until the workflow reaches its npm step, so if it failed before then, the version is still free and you can move the tag:
# fix the problem on main and commit it first
VERSION="$(node -p "require('./package.json').version")"
git push origin ":v${VERSION}" # delete the remote tag e.g. git push origin :v1.0.3
git tag -d "v${VERSION}" # delete it locally
git tag -a "v${VERSION}" -m "${VERSION}" # re-tag at the fixed commit
git push origin "v${VERSION}"The fix commit must leave package.json on that same version, or the consistency check will reject
the tag. If npm did already publish, do not reuse the version — that release is immutable. Bump to
the next patch instead; the guarded npm step means a re-run skips what already succeeded.
Contributing
Contributions are welcome! Please feel free to submit a pull request.
Acknowledgments
Available Tools
7 toolsget_author_infoGet author detailsARead-only
Get detailed information for a specific author using their Open Library Author Key (e.g. OL23919A).
Inputs: author_key (required).
get_author_photoGet author photo URLARead-only
Get the URL for an author's photo using their Open Library Author ID (OLID e.g. OL23919A). Reports when no photo exists rather than returning a URL to a blank placeholder.
Inputs: olid (required).
get_authors_by_nameFind authors by nameARead-only
Search for author information on Open Library. Returns at most limit authors (default 10) together with num_found, the total number of matches; page through them with offset. Each result's key can be passed to get_author_info for that author's full record.
Inputs: name (required), limit, offset.
get_book_by_idGet book by identifierARead-only
Get detailed information about a book using its identifier (ISBN, LCCN, OCLC, OLID).
Inputs: idType (required), idValue (required).
get_book_by_titleFind books by titleARead-only
Search for a book by its title on Open Library. Returns at most limit results (default 10) together with num_found, the total number of matches; page through them with offset. Each result carries best_edition — one edition of the work, with its isbn_13/isbn_10 where Open Library has them, and its edition_key, which can be passed to get_book_by_id as { idType: "olid" } for that edition's full record.
Inputs: title (required), limit, offset.
get_book_coverGet book cover URLARead-only
Get the URL for a book's cover image using a key (ISBN, OCLC, LCCN, OLID, ID) and value. Reports when no cover exists rather than returning a URL to a blank placeholder.
Inputs: key (required), value (required), size.
search_booksSearch booksARead-only
Search Open Library across titles, authors, subjects, places, people, publishers and ISBNs. Provide at least one search criterion: q, title, author, subject, place, person, publisher, isbn; combining several narrows the search. Returns at most limit results (default 10) together with num_found, the total number of matches; page through them with offset. Each result carries best_edition — one edition of the work, with its isbn_13/isbn_10 where Open Library has them, and its edition_key, which can be passed to get_book_by_id as { idType: "olid" } for that edition's full record.
Inputs: q, isbn, sort, limit, +8 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Most tools are clearly separated by resource and action, but get_book_by_title overlaps heavily with search_books since it returns the same result structure and is essentially a subset of the general search. The book/author detail and cover/photo tools are unambiguous.
Naming mostly follows a consistent get_<resource>_by_<qualifier> pattern, e.g. get_book_by_id, get_book_by_title, get_author_photo. search_books breaks the get_ convention but remains readable and predictable alongside the others.
Seven tools is well-scoped for a read-only Open Library server. Each tool addresses a distinct lookup need without the collection feeling bloated or thin.
The surface covers general book search, book lookup by ID/title, author search, author details, author photos, and book covers. Minor gaps exist, such as no direct endpoint for works or edition lists beyond indirection through edition_key, but core reading workflows are covered.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
A Model Context Protocol server for Wix AI tools
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Related MCP Servers
- FlicenseBqualityDmaintenanceA Model Context Protocol server implementation that can be run directly or through Docker, enabling AI assistants to interact with external systems through the MCP standard.2-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that exposes tools for querying a bookstore inventory, allowing AI agents to search and retrieve book information via the Model Context Protocol.547 npm1MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that enables searching books and authors, fetching editions, browsing subjects, and resolving cover images from Open Library.302 npm4Apache 2.0
- AlicenseNot gradedqualityCmaintenanceMCP server for Google Books API, enabling volume details, ISBN lookup, and bookshelf access via natural language queries.149 npm1MIT