Uooks logo

Uooks

Searches Open Library for books, editions, authors, and canonical works through four MCP tools.

Install Uooks

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "uooks": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-books"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

The uooks MCP server connects AI clients to Open Library for book discovery and reference lookups. It provides tools for searching titles, retrieving edition details by ISBN, looking up authors, and inspecting canonical works across editions. Use the uooks MCP server when an agent needs bibliographic metadata, descriptions, subjects, publication dates, or cover URLs without an API key. It can run through the Pipeworx gateway or locally as a stdio MCP server.

Use cases

  • Search for books by title, author, or keyword
  • Retrieve edition metadata from an ISBN
  • Inspect a canonical work across its editions
  • Look up author biographies from Open Library keys
  • Fetch book data over HTTP without an MCP client

Key features

  • Book search by title, author, or keyword
  • Edition lookup by ISBN-10 or ISBN-13
  • Author profile retrieval
  • Canonical work lookup
  • MCP gateway and local stdio modes
  • HTTP tool access through Pipeworx

Tools4

What Uooks lets your agent do. Expand a tool for its parameters.

Self-reported~218 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

6/6 checks healthy over the last 33d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 14d ago via OSV.dev · @pipeworx/mcp-books (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads401Package downloads in the last 30 days.
Last commit2d agoMost recent push to the default branch.
Tools exposed4Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Uooks works

What uooks does

The uooks MCP server exposes Open Library data for book-focused research and retrieval. It belongs to the 🔎 Search & Data Extraction category and is intended for agents that need structured bibliographic information rather than general web search.

The service provides four book-related tools:

  • search_books finds books using a title, author, or keyword query. Results include titles, authors, publication years, ISBNs, and cover image URLs.
  • get_book retrieves information about a particular edition using an ISBN-10 or ISBN-13. Its response can include the title, publication date, page count, up to 10 subjects, a description, a cover URL, and author keys.
  • get_author retrieves an Open Library author profile from an author key such as OL23919A. Results include the name, life dates when available, a biographical summary, and a Wikipedia URL.
  • get_book_work retrieves the canonical work record identified by a work ID such as OL45804W. This represents the book concept across editions and returns its title, description, first publication date, subjects, and author keys.

How it works

The uooks MCP server can be accessed through the Pipeworx gateway at https://gateway.pipeworx.io/books/mcp, or through the full gateway at https://gateway.pipeworx.io/mcp. The pack endpoint lists the four book tools along with shared Pipeworx meta-tools. Its initialize response is the authoritative source for the tools available at a given time.

A typical lookup starts with search_books. An agent can then use an ISBN from the search result with get_book, or use a W-suffixed work ID with get_book_work. Author keys returned by book or work lookups can be passed to get_author. The gateway also supports the ask_pipeworx meta-tool for questions in plain English and exposes HTTP tool calls under the gateway's /v1/tools/ path.

Setup and configuration

The gateway connection requires an MCP client that accepts a remote URL. No account is needed for the first gateway calls. Open Library access is described as free and requiring no authentication.

The uooks MCP server also runs locally through the package @pipeworx/mcp-books:

config.json
{
  "mcpServers": {
    "books": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-books"]
    }
  }
}

This local mode communicates over stdin and stdout and exposes only the pack's four tools. It does not include the shared gateway meta-tools or gateway routing. Running npx -y @pipeworx/mcp-books directly can be used to confirm that the local server starts.

Tools and capabilities

Use search_books for discovery, especially when you do not yet have an ISBN or Open Library identifier. Use get_book when edition-specific details matter, since different editions can have different publication dates, page counts, descriptions, or covers. Use get_book_work when the request concerns a title across editions, and get_author for author biography data connected to a result.

The gateway can also be called without an MCP client by sending JSON over HTTP. For example, the README uses POST https://gateway.pipeworx.io/v1/tools/books_search_books with a JSON query. This provides an alternative for applications that can make HTTP requests but do not directly speak MCP.

Limitations and notes

The integration is independent and unofficial; it is not affiliated with, endorsed by, or published by Open Library. Edition lookups require an ISBN, while work and author lookups require the relevant Open Library identifiers. The gateway pack endpoint includes additional shared tools, so its reported tool count is larger than the four book tools. Use the standalone package when only the book tools are wanted without those shared gateway capabilities.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Uooks

uooks is an MCP server that connects AI clients to the Open Library API. Its main tools search for books, retrieve edition details by ISBN, fetch author profiles by author key, and retrieve canonical work records by work ID. The integration is free, requires no Open Library authentication, and can run through Pipeworx or locally.

Install it by configuring an MCP client to run `npx -y @pipeworx/mcp-books` with the `books` server name. The package runs locally over stdin and stdout and does not require a Pipeworx account. You can also connect to the hosted Pipeworx MCP endpoint using its URL.

Yes, uooks works with Cursor through the hosted Pipeworx MCP endpoint. Add `https://gateway.pipeworx.io/books/mcp` as an MCP server URL. Cursor can then access the book tools listed by that endpoint, along with shared Pipeworx meta-tools.

Use the `get_book` tool with an ISBN-10 or ISBN-13. It returns edition data such as the title, publication date, page count, subjects, description, cover URL, and author keys. Use `search_books` first if you need to find an ISBN.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewUooks AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/uooks?style=directory)](https://allmcps.com/mcp/uooks)
HTML Embed
<a href="https://allmcps.com/mcp/uooks"><img src="https://allmcps.com/api/badge/uooks?style=directory" alt="Uooks on AllMCPs" /></a>