Directmedia MCP
This MCP server gives agents access to local Directmedia "Digitale Bibliothek" CD-ROM volumes: discovery, metadata, table-of-contents navigation, decoded full-text reading/search, and EPUB export.
Configure the library —
set_library_path(path)points the server at your local Digitale Bibliothek folder.Browse the collection —
list_volumes()enumerates all volumes (DBxxx, DBSKxx, DBSOxx) with metadata.Inspect a volume —
get_volume_info(volume_id)returns metadata and file inventory;analyze_volume_structure(volume_id)gives a file-format overview.Navigate contents —
get_navigation_tree(volume_id)returns the table of contents/structure.Read text —
get_text_content(volume_id, start_pos, length)extracts decoded book text from a starting record position.Search text —
search_text(query, volume_id?, limit)does substring matching across one volume or all volumes.Export e-books —
convert_volume_to_epub_file(volume_id, output_dir)converts a single volume to EPUB;batch_convert_to_epub(output_dir, volume_ids?)does several or all.Note: the README also advertises a
textgridtool for public-domain texts, but it is not present in this schema.
Integrates with a local Ollama instance (default port 11434) to power the 'Ask the library' chat feature: a local LLM answers questions using passages retrieved from semantically indexed volumes, with citations linking back to the reader.
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., "@Directmedia MCP search for Nietzsche quotes in the philosophy volume"
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.
Directmedia MCP
Status (2026-10-12):
TEXT.DKIdecoded. Book text is extracted from 72 of 73 text volumes; 2,281,483 of 2,281,484 records pass the full-library gate, and spot checks against TextGrid's independent transcription match at 98%. Tables of contents link to pages in 72 volumes, and the webapp is a working alternative Digibib reader (library, contents, paged reading, ranked full-text search). Still open: the TOC page map of the two largest volumes (DB050, DB125), the Russian volume DB006's character mapping, and the originalINDEX.*search files.
📖 Installation Guide — quick start, manual setup, and troubleshooting
FastMCP server aimed at giving agents access to the Directmedia Publishing "Digitale Bibliothek" CD-ROM/DVD collection.
What this wraps
The Digitale Bibliothek was Directmedia Publishing's German e-book series (1990s-2000s): ~100+ volumes of literature,
philosophy and reference works, read with the proprietary Digibib5.exe reader. Each volume stores its content in
undocumented binary files (TEXT.DKI, TREE.DKI, INDEX.*, ...).
The public-domain part of the same corpus lives on today as the zeno.org online library, which TextGrid licensed and converted to TEI XML (see Public-domain texts without the CDs).
Related MCP server: librarian
Current state (honest)
Area | State |
Volume discovery ( | Works on a local library folder |
| Decoded: titles for all volumes, page links for 72 (not DB050/DB125) |
| Decoded (format spec); 72/73 volumes, DB006 (Russian) needs a font map |
| Real text, paged by record (about one printed page), with print page numbers and source file |
| Real text, but a linear scan; slow across the biggest volumes |
EPUB export | Real text, one EPUB per volume (not yet split into works) |
| Not analysed |
An earlier version of this README claimed text extraction worked when it did not. The loose reverse_engineer_*.py /
*huffman*.py scripts in the repo root are from that failed attempt and are kept only for reference.
How TEXT.DKI was cracked
TEXT.DKI is not compressed. Earlier attempts treated the ~400 KB offset table at the start of the file as packed
data. The records behind it are byte-coded token streams: words in CP1252, spacing, line breaks, layout and metadata
tokens. The exact token sizes came from Digibib5.exe itself: Ghidra headless decompilation of the line scanner
(FUN_00614bb4) led to an int32 size table at VA 0x00763554. With that table, every record of every volume parses
to its exact boundary. Full spec: docs/DKI_FORMAT.md. Re-run the gate any time:
uv run python scripts/dki_gate.py "L:\Multimedia Files\Written Word\Digitale Bibliothek"Public-domain texts without the CDs
If you only need public-domain works, you do not need to crack DKI at all:
zeno.org — the online library derived from the same corpus.
TextGrid Repository — Digitale Bibliothek — the zeno.org corpus as TEI XML (literature ~690 authors, philosophy ~250 authors, plus smaller collections). Annotated data and metadata are CC-BY 3.0, plain texts are public domain; credit "TextGrid".
Bulk download (texts only, ~390 MB):
https://textgridlab.org/download/digitale-bibliothek/literatur-nur-texte-2.zipPer-object export:
https://textgridlab.org/1.0/aggregator/{text|epub}/textgrid:<id>
Copyrighted CD content (lexika such as Killy, editorial commentary, modern translations) is not on TextGrid. For that you need the CDs and the DKI decoder. TextGrid's Digibib project covers the literature collection (Lessing, Goethe, Busch...); philosophers such as Kant or Nietzsche are not in it.
The textgrid tool searches, reads and exports these editions without the CDs.
MCP tools
Tool | Purpose |
| Point the server at the local Digitale Bibliothek folder |
| Enumerate volumes (DBxxx, DBSKxx, DBSOxx) |
| Volume metadata and file inventory |
| File-format overview of a volume |
| Table of contents one level at a time; each entry has its start |
| Substring search over decoded text; |
| Decoded text from record |
| One EPUB per volume from decoded text |
| Same, for several volumes |
| Public-domain editions from TextGrid: |
Quick start
git clone https://github.com/sandraschi/directmedia-mcp
cd directmedia-mcp
just # list recipes
just bootstrap # install dependencies
just serve # start the MCP serverClaude Desktop (claude_desktop_config.json):
"mcpServers": {
"directmedia-mcp": {
"command": "uv",
"args": ["--directory", "D:/Dev/repos/directmedia-mcp", "run", "directmedia-mcp"]
}
}Run directly with a library path:
uv run directmedia-mcp --library-path "L:\Multimedia Files\Written Word\Digitale Bibliothek"Volume file layout (per volume, Data\)
File | Role | Decoded? |
| Book body text | No |
| Table of contents (titles / page map) | Yes, except the large-tree map layout |
| Search indices | No |
| Cross-references | No |
| Abbreviation registry | No |
| Media | Standard formats, not wired up |
Webapp
An alternative Digibib reader in web_sota/: frontend on port 10826, backend API on 10827. Start with
web_sota\start.ps1 (set DIRECTMEDIA_LIBRARY_PATH, or the library path in Settings).
Library: all volumes, with search, filter, sort and pagination.
Volume: contents tree (expand lazily, click to read), search-index build with progress, EPUB export.
Reader (
/read/<volume>/<page>): one printed page at a time, with a breadcrumb showing where you are in the work, page jump, ← → keys, print-edition page numbers, highlighted search terms and adjustable font size.Search: ranked full-text search (SQLite FTS5) over indexed volumes, with highlighted snippets that link into the reader. Words combine with AND,
"quotes"make a phrase,word*matches a prefix. Each volume is indexed once on demand (Lessing about 2 s, Philosophie about 25 s) into%LOCALAPPDATA%\directmedia-mcp\index, orDIRECTMEDIA_INDEX_DIR.Semantic search (Search page, "Semantic" mode): finds passages by meaning, not exact words. For example, "unglückliche Liebe, die im Selbstmord endet" works without knowing the title. Results show the matching works first, then the closest passages. Each volume needs its semantic index built once from its volume page (about 90 passages/s on CPU; Goethe takes about 7 minutes).
Ask the library (chat button, bottom right): a local LLM (LM Studio on :1234 or Ollama on :11434) answers from passages retrieved from your semantically indexed volumes. Answers cite sources as [1], [2]..., and the citations link to the page in the reader. Untick "Answer from my library" for a plain chat.
REST API for the reader: /api/v1/reader/{volumes, volumes/<id>/toc, volumes/<id>/records/<n>, search, index, semantic/search, semantic/index}; chat: /api/llm/{providers, chat}.
Semantic search stack (deviation from the fleet RAG default)
LanceDB + FastEmbed as in standards/ai-rag-2026.md, with two documented deviations because the corpus is German:
Setting | Fleet default | Here | Why |
Embedding model |
|
| The English model cannot handle German. In a benchmark on DB004 (Goethe), MiniLM found Faust and the Italienische Reise for thematic queries at ~45 pages/s. |
Chunking | 1000 / 200 chars | 600 / 120 chars | MiniLM reads only ~128 tokens. |
Override the model with DIRECTMEDIA_EMBED_MODEL; indexes built with another model show as "stale". Indexes live in
%LOCALAPPDATA%\directmedia-mcp\index\semantic.
Legal
This tool is for interoperability and preservation with CD-ROMs you legally own. Directmedia content remains under its original copyright; do not redistribute extracted text from copyrighted volumes. Public-domain texts via TextGrid are subject to TextGrid's terms (CC-BY 3.0 for annotated data, credit "TextGrid").
License
MIT — see LICENSE.
Available Tools
9 toolsanalyze_volume_structureC
Analyze the file structure and format of a volume
Inputs: volume_id (required). Returns: object
batch_convert_to_epubC
Convert multiple Directmedia volumes to EPUB format
Inputs: output_dir (required), volume_ids. Returns: object
convert_volume_to_epub_fileB
Convert a Directmedia volume to EPUB format for e-book readers
Inputs: volume_id (required), output_dir (required). Returns: object
get_text_contentC
Extract text content from a volume
Inputs: volume_id (required), length, start_pos. Returns: object
get_volume_infoB
Get detailed information about a specific volume
Inputs: volume_id (required). Returns: object
list_volumesA
List all available Directmedia volumes/bände
Returns a list of all volumes in the Digitale Bibliothek collection with metadata about each volume.
Inputs: no named parameters. Returns: result
search_textC
Search for text across volumes
Inputs: query (required), limit, volume_id. Returns: result
set_library_pathB
Set the path to the Digitale Bibliothek collection
Inputs: path (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Most tools are clearly distinct: list_volumes enumerates all volumes while get_volume_info targets a single one; search_text finds passages and get_text_content extracts full content. The only minor overlap is between get_navigation_tree and analyze_volume_structure, but descriptions indicate different kinds of structure (user-facing navigation vs. technical file format).
All tool names follow a consistent snake_case verb_noun pattern, e.g., list_volumes, get_volume_info, search_text, get_navigation_tree. The batch conversion tool (batch_convert_to_epub) is a minor variation but still fits the overall convention. No mixed casing or unpredictable verb usage.
Nine tools is well within the ideal range for a domain-specific server. Each tool maps to a clear need: discovery, metadata, search, text retrieval, structure, configuration, and conversion. The set is compact but not sparse, with no redundant tools.
The set covers the full workflow for a digital library server: list and inspect volumes, search and read content, navigate structure, set the library path, and convert to EPUB including batch conversion. Since the domain is a read-only archive, CRUD operations like update/delete are not missing—they are out of scope.
Related MCP Connectors
Complete classical & world literature — search + cite exact passages, facing sources, 50+ languages.
Multi-engine scholarly research server for search, traversal, full text, and reading lists.
Academic literature search, retrieval, and private library management on top of OpenAlex.
Federated search of books and papers, BibTeX/RIS citations, open-access retrieval and reading.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables search and reading of Project Gutenberg books with tools for searching by title/author/subject and fetching word-range slices of book text.MIT
- AlicenseAqualityCmaintenanceEnables browsing, searching, and quote verification of a local ebook library via MCP, providing deterministic RAG with no embeddings or network.62MIT
- AlicenseNot gradedqualityBmaintenanceProvides tools to read and compare scripture text from local Paratext project folders, enabling natural-language queries for verses, chapters, books, and cross-project comparisons.1ISC
- AlicenseNot gradedqualityCmaintenanceEnables searching and reading a library of PDF books page by page, and verifying whether a quote appears on its cited page.12 npmISC