Provides tools for searching Douban book metadata and importing book details such as cover, author, synopsis, ISBN, and rating into the bookshelf.
Click on "Deploy 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., "@bookshelf Search 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.
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
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
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/*）
pnpm build # 构建全部 workspace
pnpm typecheck # 全包类型检查
pnpm --filter @bookshelf/server mcp:test # MCP 端到端测试将以下配置加入 MCP 客户端（如 Claude Desktop / Cursor）：
{
"mcpServers": {
"bookshelf": {
"url": "http://localhost:3000/mcp"
}
}
}# 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）。
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 |
This server cannot be deployed
Search Chinese books with Douban ratings, AI book guides and curated toplists. Free, no API key.
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.
