bookshelf
Provides tools for searching Douban book metadata and importing book details such as cover, author, synopsis, ISBN, and rating into the bookshelf.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@bookshelfSearch Douban for '1984' and add it to my reading list"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Bookshelf
个人书架应用:书籍管理 + 豆瓣元数据抓取 + MCP 服务。
前端:React 18 + Vite(纯静态)
后端:Fastify 单进程(REST API + MCP + 静态托管)
数据库:better-sqlite3 + Drizzle(迁移内联在代码中)
元数据:cheerio 抓取豆瓣读书
功能
书籍增删改查、阅读状态(想读/未读/在读/已读)、标签分类、置顶
豆瓣元数据搜索与一键导入(封面、作者、简介、ISBN、评分等)
书架筛选(按状态 / 标签 / 关键词)
MCP 服务:10 个工具(豆瓣搜索、增删改查、标签),可供 Claude / Cursor 等客户端调用
Related MCP server: mcp-server-weread
快速开始
pnpm install
pnpm dev # 并行启动 server(:3000) 和 web(:5173)前端:http://localhost:5173(`/api`、`/covers` 代理到 3000)
后端:http://localhost:3000(REST
/api/*、MCP/mcp、封面/covers/*)
常用命令
pnpm build # 构建全部 workspace
pnpm typecheck # 全包类型检查
pnpm --filter @bookshelf/server mcp:test # MCP 端到端测试MCP 接入
将以下配置加入 MCP 客户端(如 Claude Desktop / Cursor):
{
"mcpServers": {
"bookshelf": {
"url": "http://localhost:3000/mcp"
}
}
}部署(Docker)
# 构建并推送镜像(交叉编译到 amd64)
docker buildx build --platform linux/amd64 -t lijf0406/bookshelf:latest . --push
# 服务器端(需预建 external 网络 web-network)
docker compose pull && docker compose up -d数据目录由 BOOKSHELF_DATA_DIR 控制(默认 data/),内含 bookshelf.db、covers/、logs/。日志按天轮转,保留天数由 BOOKSHELF_LOG_DAYS 控制(默认 14)。
项目结构
包 | 职责 |
| React 18 + Vite 前端 |
| Fastify:REST API + MCP + 静态服务 |
| 纯类型 / 常量 |
| better-sqlite3 + Drizzle,迁移内联 |
| cheerio 抓取豆瓣元数据 |
协议
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Connect AI to your flomo notes. Search, create, edit notes and manage tags via MCP.
The media memory layer for AI agents and their humans. Your AI client gets 29 tools to search your collection, add items, update ratings, preview music, and find patterns across everything you've read, watched, and listened to.
Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent.
- AchriomOAuthcom.achriom
Media memory for AI agents and their humans: books, movies, music, shows, anime, podcasts, games.
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables management of Micro.blog book collections through natural language, allowing users to organize bookshelves, add/move books, and track reading goals. Built with FastMCP for reliable integration with Claude Desktop.11MIT
- FlicenseAqualityFmaintenanceAn MCP server enabling LLMs to access WeChat Reading bookshelf, notes, highlights, and reviews via tools like get_bookshelf, search_books, and get_book_notes_and_highlights.4143170-
- AlicenseNot gradedqualityCmaintenanceEnables AI clients to read and write local Apple Books library, collections, and annotations. Supports searching, exporting, and modifying books and highlights via MCP tools.MIT
- AlicenseBqualityAmaintenanceConnects AI assistants to the Hardcover book library, enabling natural language book searches, reading status updates, list management, and library exploration.335MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/LiJF0406/bookshelf'
If you have feedback or need assistance with the MCP directory API, please join our Discord server