Goodreads MCP

Goodreads MCP

Enables access to Goodreads shelves and reading history via MCP tools, using RSS feeds and CSV exports without requiring a password.

Category
访问服务器

README

Goodreads MCP

Use your Goodreads shelves and reading history from Claude Code, Codex, and other Model Context Protocol clients—without sharing a Goodreads password.

Goodreads MCP reads supported Goodreads RSS feeds and optional Goodreads CSV exports. The local server runs entirely on your machine. The remote server adds OAuth 2.1 login, per-account storage, and a Streamable HTTP MCP endpoint on Cloudflare Workers.

[!IMPORTANT] Goodreads retired its public API. This project does not scrape Goodreads, collect session cookies, or use private Goodreads APIs. RSS is limited to roughly the most recent 100 books on each shelf; import a CSV export for complete history.

Tools

Tool Purpose
list_shelves List shelves found in RSS or an imported library
get_reading_list Read a shelf with an optional result limit
get_currently_reading Read the currently-reading shelf
get_recently_read Return recently completed books
reading_stats Calculate counts, ratings, pages, and pace, optionally by year
search_library Search your own library by title, author, or ISBN
get_book Find a library book and enrich ISBN metadata through Open Library

Run locally

Requirements: Node.js 20 or newer and a Goodreads profile user ID. For RSS access, open My Books, find the RSS link at the bottom of a shelf, and copy the key query parameter. Treat it as a secret.

export GOODREADS_USER_ID=12345678
export GOODREADS_RSS_KEY=your-rss-key
npx goodreads-mcp

GOODREADS_RSS_KEY is optional for public feeds. You can also set GOODREADS_CSV_PATH to a Goodreads library export for complete local history.

Claude Code

claude mcp add goodreads \
  --env GOODREADS_USER_ID=12345678 \
  --env GOODREADS_RSS_KEY=your-rss-key \
  -- npx -y goodreads-mcp

Codex

# ~/.codex/config.toml
[mcp_servers.goodreads]
command = "npx"
args = ["-y", "goodreads-mcp"]

[mcp_servers.goodreads.env]
GOODREADS_USER_ID = "12345678"
GOODREADS_RSS_KEY = "your-rss-key"

Use the hosted server

After deploying, connect a Streamable HTTP client to /mcp:

claude mcp add --transport http goodreads https://YOUR_WORKER.workers.dev/mcp
claude mcp login goodreads

codex mcp add goodreads --url https://YOUR_WORKER.workers.dev/mcp
codex mcp login goodreads

The OAuth login opens the Worker's connect page. Paste your Goodreads profile URL (for example https://www.goodreads.com/user/show/12345678-name) and optional RSS key. The OAuth provider supports dynamic client registration, PKCE, refresh tokens, and protected-resource metadata for compatible clients.

Self-host on Cloudflare

Deploy to Cloudflare

For a manual deployment:

  1. Fork or clone this repository and run pnpm install.
  2. Create the D1 database and KV namespaces described in packages/server-remote/wrangler.toml.
  3. Apply the D1 migrations.
  4. Replace placeholder binding IDs in wrangler.toml.
  5. Add the secrets documented in packages/server-remote/README.md.
  6. Run pnpm --filter @goodreads-mcp/server-remote deploy.

Cloudflare's free plan is sufficient for personal/light use, subject to its current limits. The deploy job in CI requires CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID repository secrets.

Development

corepack enable
pnpm install
pnpm check
pnpm build

Workspace layout:

packages/core           RSS, CSV, library queries, stats, Open Library
packages/server-local   stdio MCP server published as goodreads-mcp
packages/server-remote  OAuth-enabled Cloudflare Worker and onboarding UI

See CONTRIBUTING.md for project boundaries and SECURITY.md for reporting and data-handling details.

Privacy

The local server keeps your library and credentials on your machine. A hosted deployment stores the Goodreads identity, RSS key, imported CSV rows, and OAuth grants required to serve each account. It does not receive your Goodreads password. RSS responses may be cached for up to 15 minutes. Use the authenticated delete_account MCP tool to remove stored profile and library data, then revoke the connection in your MCP client.

Open Library receives ISBN queries when get_book performs enrichment. Review the policies of Goodreads, Open Library, Cloudflare, and your MCP client before use.

Limitations and migration path

  • Goodreads RSS normally exposes only about 100 recent items per shelf.
  • Private profiles may need an RSS key or CSV-only mode.
  • Some CSV exports omit fields used by aggregate statistics.
  • If Goodreads retires RSS, the core data-source interface can support another provider. Hardcover is the intended migration candidate because it offers a documented GraphQL API and Goodreads import.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选