Directmedia MCP
Provides programmatic access to the Directmedia Publishing 'Digitale Bibliothek' collection, a 1990s German electronic book library containing 101 volumes of classic literature and philosophy with text extraction, search, and navigation capabilities.
README
Directmedia MCP 📚
FastMCP 2.13+ server for accessing Directmedia Publishing "Digitale Bibliothek" - TEXT EXTRACTION WORKING!
🎯 Overview
The Directmedia Publishing "Digitale Bibliothek" was a pioneering German electronic book collection from the 1990s, containing extensive German literature and world literature. This MCP server provides programmatic access to these classic digital books.
✅ BREAKTHROUGH: Text Extraction Working!
MISSION ACCOMPLISHED: We successfully reversed the Directmedia TEXT.DKI format!
- Discovery: TEXT.DKI files contain structured binary records, not compressed data
- Decompressor: Working Python implementation extracts readable German text
- Access: 101 volumes of 1990s literature now programmatically accessible
- Preservation: Digital cultural heritage unlocked for modern use
What was thought to be "compression" was actually a structured record format with 2-byte length headers!
📊 Collection Status
- 101 volumes discovered (DB002-DB161, DBSK01-DBSK05, DBSO01-DBSO28)
- ~14GB total content across all volumes
- Proprietary binary format from 1990s German publishing
- Latin-1 encoding with special characters for German texts
⚠️ Legal Requirement
You must legally purchase the Directmedia CD-ROMs to use this tool. See Legal Notice section below.
🗂️ Sample Volumes
| Volume ID | Title | Size | Content Type |
|---|---|---|---|
| DB002 | Philosophie von Platon bis Nietzsche | 389MB | Philosophy |
| DB003 | Geschichte der Philosophie | 113MB | Philosophy History |
| DB004 | Goethe | 360MB | Literature + Audio |
| DB005 | Lessing | 149MB | Literature |
| DB007 | Heine | 226MB | Literature |
| DB009 | Killy Literaturlexikon | 137MB | Reference |
| DB011 | Marx/Engels | 117MB | Political Philosophy |
📊 Collection Analysis
101 volumes discovered with ~50GB total content:
- DB002-DB061: Main literature collection (philosophy, literature, history)
- DBSK01-DBSK05: Schnellkurs (crash courses)
- DBSO01-DBSO28: Sonderausgaben (special editions)
🗂️ File Format Structure
Each volume uses a proprietary binary format:
Core Files (Data/):
- TEXT.DKI: Main text database (structured binary records)
- TREE.DK*: Navigation tree (table of contents)
- INDEX.*: Multiple search indices (HTX, PLX, SHX, SWX, TTX, WLX)
- LINKS.*: Hyperlinks and cross-references
- SIGEL.DAT: Abbreviations/signatures registry
Media Files:
- IMAGES/: BMP illustrations and diagrams
- WAVS/: Audio files (readings, lectures)
- TABLES/: Specialized content tables
🚀 Quick Start
Prerequisites
- Python 3.11+
- Access to Directmedia "Digitale Bibliothek" collection
- FastMCP 2.13+
Installation
pip install -e .
Basic Usage
from directmedia_mcp import DirectmediaLibrary
# Initialize library
lib = DirectmediaLibrary(r"L:\Multimedia Files\Written Word\Digitale Bibliothek")
# List all volumes
volumes = lib.list_volumes()
print(f"Found {len(volumes)} volumes")
# Search for content
results = lib.search_text("Nietzsche", "DB002") # Philosophy volume
# Extract text
content = lib.get_text_content("DB002", 0, 1000)
MCP Server Usage
# Start MCP server
python -m directmedia_mcp.server --library-path "L:\Multimedia Files\Written Word\Digitale Bibliothek"
# Or run directly
directmedia-mcp --library-path "L:\Multimedia Files\Written Word\Digitale Bibliothek"
🔧 MCP Tools
Library Management
set_library_path(path)- Configure library locationlist_volumes()- List all available volumesget_volume_info(volume_id)- Get volume metadata
Content Access
search_text(query, volume_id, limit)- Search across volumesget_text_content(volume_id, start_pos, length)- Extract textget_navigation_tree(volume_id)- Get table of contents
EPUB Conversion ⭐ NEW
convert_volume_to_epub_file(volume_id, output_dir)- Convert single volume to EPUBbatch_convert_to_epub(output_dir, volume_ids)- Convert multiple volumes to EPUB
Analysis
analyze_volume_structure(volume_id)- File format analysis
📋 Volume Overview
| Volume ID | Title | Size | Content Type |
|---|---|---|---|
| DB002 | Philosophie von Platon bis Nietzsche | 267MB | Philosophy |
| DB003 | Geschichte der Philosophie | 180MB | Philosophy |
| DB004 | Goethe | 150MB | Literature + Audio |
| DB005 | Lessing | 75MB | Literature |
| ... | ... | ... | ... |
🔍 Technical Details
Binary Format Analysis
TEXT.DKI Structure:
- Header: 256 bytes with section offset table
- Content: Structured binary records (not compressed!)
- Each record: 2-byte length + 1-byte type + text content
TREE.DK Structure:*
- DKA: Navigation tree with entry counts and offsets
- DKI: Tree structure data
INDEX Files:
- HTX: Hypertext index for navigation
- PLX: Plaintext index for full-text search
- SHX/SWX: Specialized search indices
- TTX: Title index
- WLX: Word list index
Known Limitations
- Proprietary Format: No official documentation available
- Advanced Features: Some INDEX and TREE.DK* structures still being analyzed
- Encoding: Primarily Latin-1 with some UTF-8 elements
- Media Content: Images and audio files not yet processed
Recent Achievements ✅
- [x] TEXT.DKI Decompression: Successfully reversed structured binary record format
- [x] Text Extraction: Working decompressor extracts readable German text
- [x] EPUB Conversion: Convert volumes to modern e-book format
- [x] MCP Integration: Full programmatic access via FastMCP server
- [x] Volume Management: Complete 101-volume library access
- [x] TREE.DKI Navigation: Table of contents successfully parsed
📖 EPUB Conversion Feature
Convert extracted Directmedia text content into modern EPUB format for e-book readers!
What It Does
- Extracts readable text from Directmedia
.DKIfiles - Formats content with proper HTML structure and CSS styling
- Creates valid EPUB 3.0 files compatible with all e-book readers
- Preserves German text encoding and special characters
- Adds metadata including title, author, and volume information
EPUB Features
- Proper Structure: Mimetype, container.xml, OPF package, navigation
- German Typography: Optimized for German text with proper quotes and spacing
- Responsive Design: CSS styling that works on all devices
- Table of Contents: Navigation structure for easy browsing
- Metadata: Complete Dublin Core metadata for library management
Usage Examples
Convert single volume:
# Via MCP tool
convert_volume_to_epub_file("DB002", "./epub_output")
Batch convert multiple volumes:
# Via MCP tool
batch_convert_to_epub("./epub_library", ["DB002", "DB003", "DB004"])
Output Example
epub_output/
├── Goethe - Faust.epub # Volume DB004
├── Heine - Buch der Lieder.epub # Volume DB007
└── ... (more volumes)
EPUB Reader Compatibility
- ✅ Calibre (recommended for library management)
- ✅ Apple Books (iOS/macOS)
- ✅ Google Play Books
- ✅ Kindle (via conversion)
- ✅ Adobe Digital Editions
- ✅ All major e-book readers
Future Enhancements
- [ ] Complete INDEX file parsing for full-text search
- [ ] TREE.DK* advanced structure decoding
- [ ] Cross-volume search optimization
- [ ] Image extraction and processing
- [ ] Audio file handling
🤝 Contributing
This is a research project to preserve and provide access to classic digital literature. Contributions welcome for:
- Binary format analysis
- Decompression algorithms
- Search optimization
- Documentation improvements
⚖️ Legal Notice & Copyright
Important: Legal Use Required
This software tool is designed to work with legally purchased copies of Directmedia Publishing's "Digitale Bibliothek" CD-ROM collection. You must own legitimate copies of the CD-ROMs to use this tool legally.
Where to Purchase
Directmedia Publishing still operates and offers their complete collection:
- Official Website: https://www.directmedia-publishing.de/
- Product: "Digitale Bibliothek" (Complete 101-volume collection)
- Format: Available as digital downloads and physical media
- Languages: German literature and philosophy collections
Copyright Notice
- Copyright: © Directmedia Publishing GmbH
- Content: All text, images, and multimedia content remain copyrighted
- Usage: Personal, educational, and research use permitted with legal copies
- Redistribution: Not permitted without explicit permission
Disclaimer
This tool is provided for educational and research purposes to access legally obtained digital content. The authors are not responsible for misuse of this software. Ensure you comply with all applicable copyright laws in your jurisdiction.
Pirated or illegally obtained content is not supported and may violate copyright law.
📜 License
MIT License - see LICENSE file for details.
🙏 Acknowledgments
- Directmedia Publishing for pioneering electronic literature in the 1990s
- The German digital humanities community
- FastMCP framework for MCP implementation
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。