Open Library MCP server for AI agents
Let Claude, ChatGPT or your own agent read Open Library: 2 typed functions through one MCP server. No Open Library API key needed.
- Site
- openlibrary.org
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Open Library
An MCP server for Open Library alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/open_libraryEvery site
One MCP server for Open Library and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
getWorkReads one Open Library work by its id or openlibrary.org/works url.Arguments
Name Type Required workIdstringYes Returns
open_libraryWorkinterface open_libraryAuthorRef { authorId: string; name: string | null; // null only past the first 5 authors url: string; } interface open_libraryWork { workId: string; title: string; subtitle: string | null; authors: open_libraryAuthorRef[]; description: string | null; firstPublishDate: string | null; subjects: string[]; subjectPlaces: string[]; subjectPeople: string[]; subjectTimes: string[]; coverIds: number[]; coverUrl: string | null; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/open_library/getWorkCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.open_library.getWork("OL45804W");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.open_library.getWork("OL45804W"))curl -X POST https://api.bowmark.ai/v1/sites/open_library/getWork \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"workId":"OL45804W"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.open_library.getWork("OL45804W");searchSearches Open Library's book catalogue by title, author, subject or ISBN through its own search API, returning each work's id, authors, first publish…Arguments
Name Type Required querystringYes opts.limitnumber1-100, default 10.No opts.pagenumber1-based, default 1.No Returns
open_librarySearchResultsinterface open_librarySearchHit { workId: string; // "OL45804W", pass to getWork title: string; authors: string[]; authorIds: string[]; // "OL34184A" firstPublishYear: number | null; editionCount: number | null; subjects: string[]; // first 15 languages: string[]; // MARC codes, e.g. "eng" ebookAccess: string | null; // "public" | "borrowable" | "printdisabled" | "no_ebook" coverUrl: string | null; url: string; // https://openlibrary.org/works/<id> } interface open_librarySearchResults { query: string; totalResults: number; works: open_librarySearchHit[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/open_library/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.open_library.search("fantastic mr fox");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.open_library.search("fantastic mr fox"))curl -X POST https://api.bowmark.ai/v1/sites/open_library/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"fantastic mr fox"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.open_library.search("fantastic mr fox");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/open_library/<function> - OpenAPI
/v1/sites/open_library/openapi.json