Goodreads MCP vs Most Recommended Books
A side-by-side look at the Goodreads MCP and Most Recommended Books MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Goodreads MCP for art & culture work as a local process; choose Most Recommended Books for art & culture over a hosted endpoint. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Goodreads MCP when
- You need dedicated capabilities in the Art & Culture domain.
- You prefer a local stdio subprocess transport.
- You want tools like
search_books, get_book, get_reviews.
Choose Most Recommended Books when
- You need dedicated capabilities in the Art & Culture domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
search_books, get_person_recommendations, get_book_recommenders.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Art & Culture | Art & Culture |
| Quality signal | 52/100 · Good | 52/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Remote HTTP/SSE |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 1 |
| Directory activity | 0 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 12 | 6 |
| Full listing | View Goodreads MCP | View Most Recommended Books |
Tools & capabilities
Goodreads MCP tools 12
search_booksJSON autocomplete endpoint (stable) — book_id, title, author, rating, cover; `max_results` defaults to 10, but the endpoint returns about 5 matches at mostget_book__NEXT_DATA__` via the `.xml` page (stable) — details, cover, ratings histogram, every series membership, review-language breakdown (`review_language_limit`, default 5, max 25); edition `publication_date` and the work's `first_published`, `original_title`, `language`, `isbn` / `isbn13` / `asin`, `a…get_reviewsGraphQL — paginated reader reviews (text, rating, likes, date, spoiler flag, permalink); `limit` default 10, capped at 100; server-side `min_rating` / `max_rating` (1–5, min ≤ max), `sort` (`relevance` default, `newest`, `oldest`), `language` (two-letter code, as in `get_book`'s `review_languages`)…similar_booksGraphQL — paginated "readers also enjoyed" recommendations; `limit` up to 100author_booksGraphQL — paginated author bibliography, ranked by popularity, from any of their books, plus `author_url`; `limit` up to 100series_booksGraphQL — paginated series books with reading-order placement; `series_index` (zero-based, in `get_book`'s `series_memberships` order) picks the series; `limit` up to 100get_editionsGraphQL — paginated editions (format, ISBN, publisher, publication date as `publication_date` YYYY-MM-DD plus raw `publication_time` in epoch ms); `limit` up to 100book_listsGraphQL — paginated Listopia lists a book appears on (title, votes, size); `limit` up to 100popular_booksGraphQL — most popular books by release `year`, or a single `month` (1–12), ranked; `limit` capped at 50compare_booksget_book` for each id (`__NEXT_DATA__` via `.xml`) — ranks 1–10 distinct books by rating with positive/critical share; a repeated id is fetched once; more than 10 ids is refused; a book that fails comes back as an `error` entryget_shelfshelf RSS feed (stable) — books on a public shelf (rating and year as ints, `None` when absent; dates as `YYYY-MM-DD`; plus `cover`, `pages`, `my_review`); `page` starts at 1, about 100 items per page; `user_id` overrides the configured user; raises `LoginRequired` for a private profilelist_shelvesbest-effort HTML scrape of the public profile page — shelf names; raises `LoginRequired` for a private profile
Most Recommended Books tools 6
search_booksSearch Most Recommended Books' human-curated catalog by book title or author name. Returns ranked matches with author, publication year, how many verified people recommend each book, the top recommenders, a sourced quote, and a buy link. Use this when a user asks about a specific book, an author's books, or wants recommendations matching a title they half-remember. For 'who recommends X?' prefer get_book_recommenders; for 'what does person X recommend?' prefer get_person_recommendations.get_person_recommendationsReturn every book a specific person (entrepreneur, investor, author, celebrity…) has recommended, with their verified quote about each book and a link to the original source (interview, podcast, post). Use this when a user asks 'what books does Naval Ravikant recommend?', 'Tim Ferriss's favorite books', or wants reading habits of a specific public figure. Accepts a name ('Naval Ravikant') or MRB slug ('naval-ravikant').get_book_recommendersReturn every verified person who recommends a given book, each with their quote about it and a link to the original source. This is MRB's signature dataset — use it when a user asks 'who recommends Sapiens?', 'is Zero to One worth reading?', or wants social proof / expert opinions on a specific title. Accepts a title ('Sapiens') or author+title for disambiguation.get_series_reading_orderReturn the complete publication-order book list for a book series — the order the author released them, including novellas and companion volumes where cataloged. Use this when a user asks 'what order do I read John Grisham?', 'Harry Potter books in order', or how many books a series has. Accepts a series or author name ('Jack Reacher', 'Brandon Sanderson').get_listReturn one of MRB's 1,300+ consensus 'best books' lists for a topic (startups, stoicism, finance, sci-fi…). Every book on a list was recommended by at least two independent expert sources and is ranked by how many sources mention it. Use this when a user asks for 'the best X books' and you want a ranking backed by multiple experts rather than one opinion. Accepts a topic name ('startup', 'personal finance') or MRB list slug.get_summaryReturn MRB's one-page summary of a book: the overview plus chapter-by-chapter notes (~435 titles available). Use this when a user asks 'summarize Atomic Habits', 'what is Sapiens about?', or wants the key ideas without reading the book. Set full_text=true only when the user explicitly wants the complete chapter notes — they can be very long.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Goodreads MCP
{
"mcpServers": {
"goodreads-mcp": {
"command": "uvx",
"args": [
"goodreads-mcp-ai"
]
}
}
}
Most Recommended Books
{
"mcpServers": {
"most-recommended-books": {
"url": "https://mostrecommendedbooks.com/api/mcp"
}
}
}
Frequently asked questions
Goodreads MCP is categorized under Art & Culture and uses a local stdio subprocess. Most Recommended Books belongs to Art & Culture and uses a remote HTTP/SSE transport. Pick Goodreads MCP for art & culture work and Most Recommended Books for art & culture.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Goodreads MCP has no declared pricing — check the project's own site. Most Recommended Books has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add goodreads-mcp and most-recommended-books as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Goodreads MCP has a quality signal of 52/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Most Recommended Books has 52/100 (Good) with 1 views, 0 installs and 1 GitHub stars.