# Goodreads MCP (pypi · goodreads-mcp-ai)

Read-only MCP server for Goodreads (no API required): search, books, shelves, ratings

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- pypi · `goodreads-mcp-ai`: 75/100 (this document), [markdown](https://verifymcp.io/servers/danathar-goodreads-mcp-ai/goodreads-mcp-ai.md), [page](https://verifymcp.io/servers/danathar-goodreads-mcp-ai/goodreads-mcp-ai)

## Channel facts

- Registry: `pypi`
- Package: `goodreads-mcp-ai`
- Version: `2026.10.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 0 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Danathar/goodreads-mcp).
  - Clear OSI-approved license (GPL-3.0-only).
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1749 tokens (~145/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 90/100
  - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Goodreads MCP server?

Goodreads MCP runs locally as a PyPI package, launched with uvx goodreads-mcp-ai. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add danathar-goodreads-mcp-ai -- uvx goodreads-mcp-ai
```

### Cursor

```json
{
  "mcpServers": {
    "danathar-goodreads-mcp-ai": {
      "command": "uvx",
      "args": [
        "goodreads-mcp-ai"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "danathar-goodreads-mcp-ai": {
      "command": "uvx",
      "args": [
        "goodreads-mcp-ai"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add danathar-goodreads-mcp-ai -- uvx goodreads-mcp-ai
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "danathar-goodreads-mcp-ai": {
      "type": "local",
      "command": [
        "uvx",
        "goodreads-mcp-ai"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add danathar-goodreads-mcp-ai --command uvx --arg goodreads-mcp-ai
```

### Hermes

```yaml
mcp_servers:
  danathar-goodreads-mcp-ai:
    command: "uvx"
    args: ["goodreads-mcp-ai"]
```

### Netclaw

```json
{
  "McpServers": {
    "danathar-goodreads-mcp-ai": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "goodreads-mcp-ai"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add danathar-goodreads-mcp-ai -t stdio -c uvx -a goodreads-mcp-ai
```

### Other

```json
{
  "mcpServers": {
    "danathar-goodreads-mcp-ai": {
      "command": "uvx",
      "args": [
        "goodreads-mcp-ai"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-22 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 70, +21)

- [security regression] Malware scan: pass → unverified
- [security improvement] Injection markers: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.53
- [functional] Package version: 2026.9.3 → 2026.10.0

### 2026-10-06 (score 49, −32)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.27 → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-03 (score 81, +16)

- [security improvement] Malware scan: unverified → pass

## MCP tools (12)

### `search_books` (~99 tokens)

Search Goodreads for books by title/author/ISBN.

Uses the JSON autocomplete endpoint (no auth, no HTML parsing).
Returns book_id, title, author, rating info, and a cover URL.

max_results: how many to return. The autocomplete endpoint itself
    answers with at most ~5 matches, so a larger value returns what
    Goodreads sent, not more.

Input parameters:

- `max_results` (integer)
- `query` (string, required)

Output parameters:

- `result` (array)

### `get_book` (~173 tokens)

Get full details for a book by its Goodreads id (numeric, or numeric-slug
like '11870085-the-fault-in-our-stars' or '2767052.The_Hunger_Games'). An
ISBN is not a book id: find the book with search_books first.

Parses the page's embedded __NEXT_DATA__ JSON (Apollo state) rather than
scraping the DOM, which survives markup changes. Includes the full
ratings histogram, all series memberships, and review-language breakdown
— use get_reviews for the actual review text. review_language_limit controls
how many languages are returned (default 5, maximum 25).

When you cite details or ratings from this book, link to its 'url'.

Input parameters:

- `book_id` (string, required)
- `review_language_limit` (integer)

### `get_reviews` (~256 tokens)

Get reader reviews for a book — the actual review text, not just a score.

Fetches from Goodreads' GraphQL backend with true pagination, so limit
can exceed the ~30 shown on a page. Reviews come in "most relevant"
order and aggregate across all editions of the work. Each review has the
reviewer name, star rating (1-5), full text, like/comment counts, date, a
spoiler flag, a 'url' permalink (use it to cite/link), and the reviewer's
profile url.

limit: max reviews to return (capped at 100 to stay polite).
min_rating / max_rating: server-side star filters, each 1-5, e.g.
    min_rating=4 for positive reviews, max_rating=2 for the critical ones.
exclude_spoilers: drop reviews flagged as spoilers. Paging is capped, so
    a book whose reviews are mostly spoilers can return fewer than limit.

'has_more' is true when Goodreads has reviews this call did not read.

Input parameters:

- `book_id` (string, required)
- `exclude_spoilers` (boolean)
- `limit` (integer)
- `max_rating`
- `min_rating`

### `similar_books` (~86 tokens)

"Readers also enjoyed" — books similar to the given one.

Goodreads' own recommendation graph (hard to reproduce with web search).
Each result has book_id/title/author/rating/url so you can chain into
get_book or get_reviews. Results paginate in batches and limit is capped
at 100.

Input parameters:

- `book_id` (string, required)
- `limit` (integer)

### `author_books` (~80 tokens)

List an author's works (bibliography), given any of their books.

Resolves the book's primary author, then returns their works ranked by
popularity. Each result has book_id/title/author/rating/url. Results
paginate in batches and limit is capped at 100.

Input parameters:

- `book_id` (string, required)
- `limit` (integer)

### `series_books` (~139 tokens)

List the books in a series (with reading-order placement), given any
book in that series. When a book belongs to multiple series, pass the
zero-based series_index from get_book's series_memberships order.

Each entry has the series 'placement' (e.g. '1', '0.5' for a prequel),
'is_primary' (a main-sequence entry vs companion), and the usual
book_id/title/author/rating/url. Results paginate in batches and limit is
capped at 100.

Input parameters:

- `book_id` (string, required)
- `limit` (integer)
- `series_index` (integer)

### `get_editions` (~66 tokens)

List published editions of a book (formats, ISBNs, publishers, dates).

Useful for "which edition / format / ISBN" questions. Results paginate in
batches and limit is capped at 100.

Input parameters:

- `book_id` (string, required)
- `limit` (integer)

### `book_lists` (~101 tokens)

List the Listopia lists a book appears on (e.g. "Best Dystopian
Fiction"), ordered by popularity.

Each list has its title, total member votes, how many books it contains,
and a 'url'. Good for "what kind of book is this / what's it grouped with"
and for discovery. Results paginate in batches and limit is capped at 100.

Input parameters:

- `book_id` (string, required)
- `limit` (integer)

### `popular_books` (~185 tokens)

Most popular books by release date — Goodreads' "Popular by date" chart.

Ranks the books/works released in a given year (or a specific month of a
year) by how many Goodreads members have added them. Mirrors the
goodreads.com/book/popular_by_date/<year>[/<month>] page. A year or month
Goodreads has no chart for raises an error rather than returning no books.

year: 4-digit release year.
month: optional 1-12 for a single month; omit for the whole year.
limit: how many to return (capped at 50).

Each entry has rank, count (members who added it), and the usual
book_id/title/author/rating/url so you can chain into get_book/get_reviews.

Input parameters:

- `limit` (integer)
- `month`
- `year` (integer, required)

### `compare_books` (~125 tokens)

Compare several books side by side by rating and rating distribution.

Fetches each book and returns them ranked best-to-worst by average rating,
with the ratings_histogram plus 'pct_positive' (share of 4-5 star) and
'pct_critical' (share of 1-2 star) so you can judge not just the average
but how divisive each book is. Pass 2-10 book ids (from search_books etc.);
more than 10 is refused rather than silently trimmed, so split the call.

Input parameters:

- `book_ids` (array, required)

### `get_shelf` (~153 tokens)

List books on a shelf via its RSS feed (public shelves; no auth).

Common shelves: 'read', 'currently-reading', 'to-read', plus any custom
shelf name. Names are case-sensitive and must match a shelf the user has
(list_shelves gives them); any other name raises ValueError. An empty
name lists every shelf. RSS pages hold ~100 items; pass page=2,3,... for
more (pages start at 1). Defaults to the configured GOODREADS_USER_ID.

When you cite a book from a shelf, link it to its 'link' field.

Input parameters:

- `page` (integer)
- `shelf` (string)
- `user_id`

Output parameters:

- `result` (array)

### `list_shelves` (~88 tokens)

List a user's shelf names (scraped from their public profile page;
best effort). Defaults to the configured user.

Covers the exclusive shelves (read, to-read, ...) and custom shelves;
every name works as get_shelf's 'shelf' argument. Raises LoginRequired
for a private profile. The profile page may cap a very long shelf list.

Input parameters:

- `user_id`

Output parameters:

- `result` (array)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/danathar-goodreads-mcp-ai/goodreads-mcp-ai#diagnostics

## Score history

- 2026-10-23: 75
- 2026-10-22: 75
- 2026-10-21: 74
- 2026-10-20: 74
- 2026-10-19: 73
- 2026-10-18: 73
- 2026-10-17: 72
- 2026-10-16: 72
- 2026-10-15: 71
- 2026-10-14: 71
- 2026-10-13: 70
- 2026-10-12: 70
- 2026-10-06: 49
- 2026-10-04: 81
- 2026-10-03: 81
- 2026-10-02: 65
- 2026-10-01: 65
- 2026-09-30: 79
- 2026-09-29: 79
- 2026-09-28: 78
- 2026-09-27: 67
- 2026-09-26: 67

## Common questions

### What is the Goodreads MCP server?

Goodreads MCP is listed in the public MCP registry as io.github.Danathar/goodreads-mcp-ai. Read-only MCP server for Goodreads (no API required): search, books, shelves, ratings. This page covers its PyPI package (goodreads-mcp-ai).

### Is the Goodreads MCP server safe to use?

Goodreads MCP scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Goodreads MCP server expose?

Goodreads MCP exposes 12 tools: search_books, get_book, get_reviews, similar_books, author_books, and 7 more. Their descriptions and schemas cost roughly 1,551 tokens of context every time the server is loaded.

### Is the Goodreads MCP server still maintained?

Goodreads MCP is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Goodreads MCP server under?

Goodreads MCP declares the GPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/goodreads-mcp-ai/
- Socket report: https://socket.dev/pypi/package/goodreads-mcp-ai
- Repository: https://github.com/Danathar/goodreads-mcp
- Changelog RSS feed: https://verifymcp.io/servers/danathar-goodreads-mcp-ai/goodreads-mcp-ai.xml
- Changelog JSON feed: https://verifymcp.io/servers/danathar-goodreads-mcp-ai/goodreads-mcp-ai.json
- HTML version of this page: https://verifymcp.io/servers/danathar-goodreads-mcp-ai/goodreads-mcp-ai