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.

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_library
Every 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/mcp
Set it up in your client

Both 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

    NameTypeRequired
    workIdstringYes

    Returns open_libraryWork

    interface 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/getWork

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.open_library.getWork("OL45804W");

Use it from code