Repository avatar
Search & Data Extraction
v0.4.1
active

openlibrary-mcp-server

io.github.cyanheads/openlibrary-mcp-server

Search books and authors, fetch editions, browse subjects, and resolve cover images.

Documentation

@cyanheads/openlibrary-mcp-server

Search books and authors, fetch editions, browse subjects, and resolve cover images from Open Library via MCP. STDIO or Streamable HTTP.

10 Tools • 2 Catalog Resources • 1 Agent Skill

Version License Docker MCP SDK npm TypeScript Bun


Overview

Open Library's catalog of 20M+ books, editions, authors, and subjects, plus full-text search inside Internet Archive's scanned books. Search and browse, drill from a work into its editions or an author into their works, and construct cover image URLs.

Tools

ToolDescription
openlibrary_search_booksCatalog search with field filters (title, author, subject, publisher, ISBN, language), a provider-selected edition, pagination, and optional live reading availability
openlibrary_get_workFetch a work by Open Library Work ID (OL…W) — title, description, subjects, cover IDs, and author IDs
openlibrary_get_editionsList editions of a work — publishers, languages, formats, ISBNs, print run details, and edition-level credits (subtitle, by-statement, translators and other contributors)
openlibrary_get_editionResolve up to 50 distinct identifiers per call by ISBN-10, ISBN-13, OCLC, LCCN, or Open Library Edition ID (OL…M), reporting misses and unprocessed identifiers
openlibrary_search_authorsSearch authors by name — returns Author IDs, birth/death dates, top works, and subject associations
openlibrary_get_authorFetch author detail by Open Library Author ID (OL…A) — bio, dates, photo IDs, and linked identifiers from Wikidata, VIAF, ISNI, Goodreads, and LibraryThing
openlibrary_get_author_worksList works by an author — titles, cover IDs, and Work OLIDs for drilling into editions or details
openlibrary_get_subjectBrowse works by subject tag — returns matching works with edition counts and cover IDs plus the total work count
openlibrary_search_insideFull-text search inside the scanned text of Internet Archive books — returns matching items with snippets
openlibrary_get_cover_urlResolve a cover image URL for a book or author photo in S/M/L size — returns a direct HTTPS URL embeddable in markdown

Resources

ResourceDescription
openlibrary://works/{work_id}Work detail by Open Library Work ID — title, description, subjects, cover IDs, and author IDs as injectable context
openlibrary://authors/{author_id}Author detail by Open Library Author ID — name, bio, dates, photo IDs, and linked external identifiers as injectable context

Both resources mirror data also available via openlibrary_get_work and openlibrary_get_author — useful for clients that don't surface MCP resources.

Agent skill

openlibrary-guide covers edition selection, bibliography resolution, passage identification, and incomplete metadata. It is included in npm, Docker, and desktop bundles and served through MCP skill discovery and skill:// resources.

Capability reference

Paginated tools return at most 1,000 rows per call, except openlibrary_search_inside at 100. Larger positive integer limits are clamped with a notice showing the applied limit and, when a later page exists, the next offset. OPENLIBRARY_CLAMP_LIMITS=false restores schema rejection above 100 rows. Text and structured output carry the same complete domain data, including arrays and numeric precision.

openlibrary_search_books tool

  • Free-text query with Solr field prefixes (title:, author:, subject:, publisher:, isbn:, language:, plus ia:<ia_identifier>, author_key:<author_id>, first_publish_year:[1900 TO 1950], ebook_access:public) or dedicated filter parameters; 1–1000 results per page (default 10), offset pagination
  • A search needs at least one non-blank query, title, author, subject, publisher, or isbn; blank criteria count as absent, and language or sort alone fails as no_search_criteria before any request
  • sort: relevance (default), new, old, rating, editions
  • language accepts a 3-letter MARC code, an ISO 639-2/T code (deu, fra, …) in any case, or a translatable 2-letter ISO code; a code that is neither a MARC code nor an Open Library language record fails as unknown_language_code rather than silently matching nothing. Chinese is indexed under both chi and cmn
  • include_availability adds live Internet Archive borrow/read status, off by default, at the cost of one additional search request per 100 returned works with an Internet Archive scan; flags Open Library leaves out are omitted rather than reported as false, and availability: null means none was returned for the work. A lookup that does not complete never fails the search: those works read null and the notice names them as unknown
  • Returns work-level records with edition counts, cover IDs, subjects, and Internet Archive identifiers
  • Optional matching_edition and matching_edition_count preserve the Search API's selected edition and matching count. The selected edition is provider-ranked; it does not prove that every unfielded search term matches that edition
  • invalid_search_query reports upstream HTTP 422 validation with recovery guidance

openlibrary_get_work tool

  • Fetch by Open Library Work ID (OL…W), optionally /works/-prefixed; anything else — an ISBN, an edition or author OLID — fails input validation before any request, naming openlibrary_get_edition (id_type: "isbn") as the route from an ISBN to its work
  • Returns title, description, subjects (plus place/time/people breakdowns), cover IDs, and author IDs — no author names (use openlibrary_get_author or openlibrary_search_books)
  • A merged work ID stays reachable — the redirect chain is followed to the canonical record, work_id reports the canonical ID, and an enrichment notice names both IDs when they differ
  • not_found when the Work ID doesn't exist or its redirect chain reaches no work

openlibrary_get_editions tool

  • List editions of a work by Work ID (OL…W), optionally /works/-prefixed; 1–1000 per page (default 10), offset pagination, with the requested offset echoed in the output; an offset at or past the total returns an empty page with a notice naming the last offset that returns a result
  • Same work_id validation as openlibrary_get_work — an ISBN resolves to its work through openlibrary_get_edition (id_type: "isbn")
  • Returns ISBN-10/13, publishers, languages, page count, cover IDs, and edition OLIDs (OL…M), plus physical_format, edition_name, and the edition-level credits subtitle, by_statement, contributors (name and role), contributions (legacy credit strings), and translated_from (MARC language codes) when recorded, all verbatim
  • A merged work ID stays reachable — the editions of the canonical work come back under its ID in work_id, with an enrichment notice naming both IDs; a live work costs one request
  • not_found when the Work ID doesn't exist or its redirect chain reaches no work

openlibrary_get_edition tool

  • Accepts 1–1,000 input strings, deduplicates exact strings, and processes the first 50 distinct identifiers in one upstream batch; the remainder is returned as unprocessed for resubmission. Every identifier shares one id_type: isbn (10 or 13 digits, an ISBN-10 may end in an X check digit), oclc (numeric), lccn (any non-blank string), or olid (OL…M). With OPENLIBRARY_CLAMP_LIMITS=false, the input array is limited to 50 entries
  • Partial success: identifiers that resolve return in editions (request order), each row carrying its identifier exactly as supplied; the rest land in unresolved with invalid_identifier (malformed or blank, never sent upstream) or not_found (well-formed, no record) — the call fails only when nothing resolves
  • upstream_unavailable (retryable) when Open Library's batch lookup itself fails — an HTTP error status other than a rate limit, or an HTML page or other body that is not JSON — so an upstream outage never reads as a missing edition
  • Authors come inline — the edition's own credits, or ones marked source: "work" recovered from the parent work when the edition itself lists none; if those lookups fail, the batch still returns, and an enrichment notice names the editions whose authors are missing or shown by ID
  • Returns ISBN-10/13, OCLC, LCCN, LC call numbers, publishers, all cataloged languages, page count, cover IDs, parent work ID, and an Internet Archive ebook_url when one exists. The singular language remains the first cataloged language; physical_format, edition_name, and the credits subtitle, by_statement, contributors, contributions, and translated_from preserve the catalog's wording when present
  • If no processed identifier resolves, the typed error also carries every unprocessed identifier in its data and recovery hint

openlibrary_search_authors tool

  • Search by name — partial and alternate names match; 1–1000 per page (default 10), offset pagination; a blank query fails as no_search_criteria
  • Returns Author ID (OL…A), alternate names, birth/death dates, top work, work count, top subjects, and average rating

openlibrary_get_author tool

  • Fetch by Author ID (OL…A, in any case — it is upper-cased before the request); a leading /authors/ prefix is stripped
  • Returns bio, birth/death dates, photo IDs, and linked identifiers (Wikidata, VIAF, ISNI, Goodreads, LibraryThing)
  • A merged author ID stays reachable — the response is the canonical record, and an enrichment notice names the canonical ID when it differs from the one requested
  • not_found when the Author ID doesn't exist, names a record that is not an author (a work or edition OLID), or its redirect chain reaches no author

openlibrary_get_author_works tool

  • List works by Author ID (OL…A, in any case); 1–1000 per page (default 20), offset pagination, with the requested offset echoed in the output; an empty page with a positive total carries a past-end notice
  • Returns title, first-publish date, cover IDs, and Work ID (OL…W) per work; for an author's works ranked by edition count, use openlibrary_search_books with query author_key:<author_id> and sort editions
  • A merged author ID stays reachable — an enrichment notice names the canonical ID when it differs from the one requested
  • not_found when the Author ID doesn't exist, names a record that is not an author (a work or edition OLID), or its redirect chain reaches no author

openlibrary_get_subject tool

  • Subject name is trimmed, lowercased, and normalized from whitespace to underscores; 1–1000 per page (default 12), offset pagination, with the requested offset echoed in the output; an offset at or past the total carries a past-end notice
  • A place:, person:, or time: prefix browses a place, person, or period, taking a value from openlibrary_get_work's subject_places, subject_people, or subject_times verbatim (place:London (England)); whitespace after the prefix is dropped
  • Blank input fails as invalid_subject before any request
  • Returns canonical subject name, normalized subject key, subject_type (place, person, time, or subject), total work count, and per-work author names, edition count, and cover ID
  • Empty results carry a recovery notice suggesting a different word form, synonym, or broader term — subject tags are user-contributed and inconsistent

openlibrary_search_inside tool

  • Full-text search across Internet Archive's scanned book text — the only tool that answers "which book contains this passage?"; quote a phrase for an exact match, unquoted terms match independently
  • Usually takes 10–30 s against the live index, far above the metadata tools — reach for it deliberately, not as a general book search
  • 1–100 results per page (default 10), offset pagination; each result carries a relevance score comparable only within its own result set. The full-text index serves only its first 10,000 results: a page that would run past them is shortened with a notice, and an offset of 10000 or more fails as offset_past_result_window. A blank query fails as no_search_criteria
  • Results key on Internet Archive ia_identifier, not Open Library work IDs — pass it to openlibrary_search_books as query ia:<ia_identifier> to reach the work and, in matching_edition, the edition holding that scan
  • upstream_unavailable (retryable) when the index answers without a result set, so a failed search never reads as "no book contains this"

openlibrary_get_cover_url tool

  • Resolves a cover or author-photo URL from id (numeric), isbn (10 or 13 digits, an ISBN-10 may end in an X check digit), or olid (OL…M for target: "book", OL…A for target: "author", in any case — the URL carries it upper-cased); size is S/M/L (default M)
  • Identifiers are validated locally before any request — path separators, .., and control characters fail as invalid_identifier, and an author lookup by isbn fails as invalid_target
  • The tool constructs the URL without fetching it; a returned URL does not verify that a cover exists
  • Output URL is ready to embed directly as ![cover](url)

openlibrary://works/{work_id} resource

  • Same fields as openlibrary_get_work, as injectable application/json context for a conversation about a specific book
  • A work-OLID-shaped work_id in any case is upper-cased before the request
  • work_id comes from openlibrary_search_books or openlibrary_get_author_works; a merged ID resolves to the canonical work, whose ID the returned work_id carries, and an ID that is not a work (an edition or author OLID) is not found

openlibrary://authors/{author_id} resource

  • Same fields as openlibrary_get_author, as injectable application/json context for a conversation about a specific author
  • An author-OLID-shaped author_id in any case is upper-cased before the request
  • author_id comes from openlibrary_search_authors; a merged ID resolves to the canonical author, whose ID the returned author_id carries, and an ID that is not an author (a work or edition OLID) is not found

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Open Library-specific:

  • Open Library Search, Search Inside (full-text), Books, Authors, and Subjects APIs, cover URL construction, and Internet Archive availability lookups
  • Work → editions and author → works drill-down, with explicit OLID cross-links between tool outputs
  • Configurable User-Agent header (OPENLIBRARY_USER_AGENT) identifying the server per Open Library's bot-blocking convention
  • Batch edition resolution — up to 50 ISBN/OCLC/LCCN/OLID identifiers in one upstream call, with per-identifier partial-failure reporting
  • Timeouts sized per endpoint class (10 s record lookups, 30 s searches, 45 s full-text) inside a 50 s retry budget, so a slow upstream is waited on and a failing one returns a classified error before a typical 60 s client timeout; gateway errors are not retried in a loop

Agent-friendly output:

  • Recovery guidance on every empty result — echoes the search criteria and suggests how to broaden a query or which offset to retry
  • Merged-record disclosure — openlibrary_get_author, openlibrary_get_author_works, openlibrary_get_work, and openlibrary_get_editions follow merge redirects and surface the canonical ID via an enrichment notice when a requested ID was merged
  • Per-item partial failure — openlibrary_get_edition returns resolved editions alongside typed unresolved reasons instead of failing the whole batch
  • Complete text and structured output, with clamp and recovery notices preserved on both surfaces

Getting started

Add the hosted server to Claude Code — no API key required:

claude mcp add --transport http openlibrary-mcp-server https://openlibrary.caseyjhand.com/mcp

Or run it locally:

claude mcp add openlibrary-mcp-server -- npx -y @cyanheads/openlibrary-mcp-server

For other clients, add this to the MCP config file:

{
  "mcpServers": {
    "openlibrary-mcp-server": {
      "command": "npx",
      "args": ["-y", "@cyanheads/openlibrary-mcp-server"]
    }
  }
}

For Docker or a source build, see Running the server.

Configuration

VariableDescriptionDefault
MCP_TRANSPORT_TYPETransport: stdio or httpstdio
MCP_HTTP_PORTHTTP server port3010
MCP_HTTP_ENDPOINT_PATHHTTP endpoint path where the MCP server is mounted/mcp
MCP_SESSION_MODEHTTP session posture: stateless, stateful, or auto. Overrides the stateless declared in src/index.ts.stateless
MCP_PUBLIC_URLPublic origin override for TLS-terminating reverse-proxy deploymentsnone
MCP_AUTH_MODEAuthentication: none, jwt, or oauthnone
MCP_LOG_LEVELLog level (debug, info, warning, error, etc.)info
MCP_GC_PRESSURE_INTERVAL_MSOpt-in Bun-only forced-GC pressure loop (ms). Recommended starting point if heap growth is observed: 60000.0 (disabled)
LOGS_DIRDirectory for log files (Node.js only)<project-root>/logs
STORAGE_PROVIDER_TYPEStorage backend: in-memory, filesystem, supabase, cloudflare-kv/r2/d1in-memory
OPENLIBRARY_USER_AGENTUser-Agent sent with all Open Library API requests. Include a contact email per community convention.openlibrary-mcp-server casey@caseyjhand.com
OPENLIBRARY_CLAMP_LIMITSClamp page limits to each page tool's ceiling (1,000 rows; 100 for openlibrary_search_inside) and process the first 50 distinct edition identifiers, returning the remainder. false restores strict input bounds of 100 rows and 50 raw identifiers.true
OTEL_ENABLEDEnable OpenTelemetryfalse

See .env.example for the full list of optional overrides.

Running the server

Local development

Requires Bun v1.4.4 or higher (or Node.js ≥ 24.0.0).

  • Clone and install:

    git clone https://github.com/cyanheads/openlibrary-mcp-server.git
    cd openlibrary-mcp-server && bun install
    cp .env.example .env   # optional overrides; no required variables
    
  • Build and run the production version:

    # One-time build
    bun run rebuild
    
    # Run the built server
    bun run start:http
    # or
    bun run start:stdio
    
  • Run checks and tests:

    bun run devcheck  # Lint, format, typecheck, security
    bun run test      # Vitest test suite
    bun run lint:mcp  # Validate MCP definitions against spec
    

Docker

docker run --rm -p 3010:3010 ghcr.io/cyanheads/openlibrary-mcp-server:latest

The image defaults to HTTP transport, stateless session mode, and logs to /var/log/openlibrary-mcp-server. To run it over stdio from an MCP client, use "command": "docker" with "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/openlibrary-mcp-server:latest"]. To build locally, run docker build -t openlibrary-mcp-server .; OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

DirectoryPurpose
src/index.tscreateApp() entry point — registers tools and resources.
src/configServer-specific environment variable parsing and validation with Zod.
src/mcp-server/toolsTool definitions (*.tool.ts) — ten tools across Search, Books, Authors, Subjects, and Covers.
src/mcp-server/resourcesResource definitions (*.resource.ts) — Work and Author.
src/services/open-libraryOpen Library service layer — API client and domain types.
skills/Published agent guidance, also served through MCP skill discovery.
tests/Unit and integration tests mirroring the src/ structure.

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

  • Handlers throw, framework catches — no try/catch in tool logic
  • Use ctx.log for logging, ctx.state for storage
  • Register new tools and resources in the createApp() arrays
  • Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.

NPM
@cyanheads/openlibrary-mcp-server
Install Command
npm install @cyanheads/openlibrary-mcp-server
Runtime: npx
NPM
@cyanheads/openlibrary-mcp-server
Install Command
npm install @cyanheads/openlibrary-mcp-server
Runtime: npx