Claude Book Agent
An MCP server that automates the generation of structured children's books using Claude Desktop.
README
Claude Book Agent
An AI-powered Model Context Protocol (MCP) server for Claude Desktop that automates the generation of structured children's books.
This project demonstrates how an AI agent can orchestrate a multi-step book creation workflow, maintain generation state, and produce publication-ready content for further editing and publishing.
Overview
Creating a high-quality children's book involves much more than simply generating text. The process requires planning the book structure, generating consistent content, handling long-running tasks, preserving progress, and producing output that can be refined for publication.
This project explores how an AI agent can automate that workflow using the Model Context Protocol (MCP) and Claude Desktop.
The current implementation provides a working MCP server that generates structured children's book content while maintaining generation state. It serves as the foundation for a larger autonomous publishing pipeline that will eventually generate stories, activities, poems, illustration prompts, and publication-ready assets with minimal manual intervention.
Features
Current Capabilities
- MCP server compatible with Claude Desktop
- AI-assisted generation of structured children's books
- Persistent state management to resume interrupted generation
- Markdown export of generated content
- Built with Node.js and JavaScript
- Extensible foundation for future AI publishing workflows
Planned Enhancements
- Modular story generation engine
- Illustration prompt generation
- Activity page generation
- Poetry generation
- DOCX and PDF export improvements
- Amazon KDP formatting
- Metadata generation
- Automated quality review
- Social media content generation
- End-to-end autonomous publishing pipeline
Technology Stack
| Technology | Purpose |
|---|---|
| Node.js | Runtime environment |
| JavaScript | Core application development |
| Model Context Protocol (MCP) | Integration with Claude Desktop |
| Claude Desktop | AI client invoking the MCP server |
| Markdown | Generated book output format |
| Git & GitHub | Version control and collaboration |
Technology Stack
| Technology | Purpose |
|---|---|
| Node.js | Runtime environment |
| JavaScript | Core application development |
| Model Context Protocol (MCP) | Integration with Claude Desktop |
| Claude Desktop | AI client invoking the MCP server |
| Markdown | Generated book output format |
| Git & GitHub | Version control and collaboration |
Architecture
User
│
▼
Claude Desktop
│
Model Context Protocol (MCP)
│
▼
Claude Book Agent (Node.js)
│
┌───────────┼───────────┐
│ │ │
▼ ▼ ▼
Story Generation State Management Export Engine
│ │ │
└───────────┼───────────┘
│
▼
Generated Children's Book
The MCP server acts as the orchestration layer between Claude Desktop and the book generation pipeline. It manages generation requests, preserves state, and produces structured output that can be extended into a complete publishing workflow.
Project Structure
book-pipeline-mcp/
│
├── index.js # MCP server implementation
├── package.json # Project configuration
├── package-lock.json # Dependency lock file
├── book_output.md # Sample generated output
├── book_state.json # Persistent generation state
├── README.md # Project documentation
└── .gitignore
Getting Started
Prerequisites
- Node.js
- Claude Desktop
- Git
Clone the repository
git clone https://github.com/YOUR_USERNAME/YOUR_REPOSITORY.git
Install dependencies
npm install
Start the MCP server
node index.js
Configure Claude Desktop to use this server through its MCP configuration.
Why I Built This
I wanted to explore how AI agents can automate complete workflows instead of solving isolated tasks.
Children's book creation involves multiple stages such as planning, content generation, maintaining consistency, exporting content, and preparing it for publishing. Rather than treating each task independently, this project demonstrates how an MCP server can orchestrate the entire workflow through Claude Desktop.
This repository represents the first milestone toward building an autonomous AI publishing platform capable of generating publication-ready children's books with minimal manual intervention.
Skills Demonstrated
This project showcases practical software engineering and AI workflow design skills, including:
- AI Agent Development
- Model Context Protocol (MCP)
- Claude Desktop Integration
- Node.js & JavaScript
- Prompt Engineering
- Workflow Automation
- State Management
- Technical Product Thinking
- Software Architecture
- Git & GitHub
Roadmap
The long-term vision for this project includes:
- Modular story generation engine
- Illustration prompt generation
- Children's activity generation
- Poetry generation
- DOCX and PDF export
- Amazon KDP formatting
- Metadata generation
- Automated quality review
- Social media content generation
- End-to-end autonomous publishing pipeline
Current Status
This project is actively under development.
The current version demonstrates a working MCP server integrated with Claude Desktop for AI-assisted children's book generation. Future iterations will focus on modular architecture, testing, enhanced exports, and a complete autonomous publishing workflow.
License
This project is released under the MIT License.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。