Skip to main content

MCP server for the BHt (Biblia Hebraica transcripta) Hebrew Bible database

Project description

bht-mcp

MCP server for the BHt (Biblia Hebraica transcripta) Hebrew Bible database at LMU Munich.

Ask your AI assistant to search, analyze, and compare 489,000+ morphologically analyzed Hebrew Bible tokens โ€” directly from your chat interface.

You:  "Compare the use of root BRสพ (create) in Genesis vs Isaiah"
AI:   [calls bht_search with Wurzel filter for each book, then bht_token_detail
       on selected tokens โ€” returns morphological breakdowns, verbal stems,
       and syntactic contexts from both books]

No Hebrew expertise is needed to get started. The AI reads the linguistic data and explains it to you.

๐Ÿ‡ฐ๐Ÿ‡ท ํ•œ๊ตญ์–ด


About BHt

BHt (Biblia Hebraica transcripta) is a digital transcription of the Hebrew Bible maintained at LMU Munich under the direction of Prof. Wolfgang Richter. It features:

  • 489,437 tokens with full morphological analysis
  • Richter transcription system โ€” Latin-script phonemic representation (e.g., barฤ(สพ) for ื‘ึธึผืจึธื)
  • 5-class part-of-speech system (Hauptwortart, Nebenwortart, Fรผgwortart, etc.)
  • Syntactic trees at word-level (Wortfรผgungsebene) and sentence-level (Satzfรผgungsebene)
  • Textual criticism annotations with Greek/Masoretic manuscript variant data
  • 8 Sirach manuscript fragments (Ben Sira, from Cairo Genizah and Masada)

Table of Contents


How It Works

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”  stdio  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”  cache miss  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚  MCP Client  โ”‚ โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ†’โ”‚  bht-mcp         โ”‚ โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ†’โ”‚  BHt Website โ”‚
โ”‚  (Claude,    โ”‚ โ†โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”‚  (local process) โ”‚ โ†โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”‚ (LMU Munich) โ”‚
โ”‚  local LLM,  โ”‚         โ”‚  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”  โ”‚              โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
โ”‚  etc.)       โ”‚         โ”‚  โ”‚ ~/.bht/    โ”‚  โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜         โ”‚  โ”‚ cache.db   โ”‚  โ”‚  โ† local SQLite cache
                         โ”‚  โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜  โ”‚
                         โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
  • Runs entirely on your machine. No remote server, no API keys, no cost.
  • Progressive caching. The first search for a book fetches all its tokens in one request. After that, searches in the same book are instant โ€” zero network calls.
  • Respectful. Built-in rate limits (1 req/s, 150 HTML pages/day) protect the university server. The tool never bulk-scrapes.

Installation & Setup

Option A: Using uv (recommended)

uv is the standard tool for running MCP servers. No separate install step needed โ€” just configure your client.

Install uv (one-time):

Platform Command
macOS brew install uv
Windows powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
Linux curl -LsSf https://astral.sh/uv/install.sh | sh

Then go directly to Setting Up Your MCP Client below.

Option B: Using pip

If you prefer a traditional install:

pip install bht-mcp

Requires Python 3.11+. If Python is not installed: python.org/downloads (Windows: check "Add Python to PATH"). macOS: brew install python. Linux: sudo apt install python3 python3-pip.


Setting Up Your MCP Client

MCP (Model Context Protocol) lets AI assistants use external tools. Choose your client below:

Claude Desktop

Edit your MCP settings (Settings โ†’ Developer โ†’ MCP Servers) and add:

If you installed with uv:

{
  "mcpServers": {
    "bht": {
      "command": "uvx",
      "args": ["bht-mcp"]
    }
  }
}

If you installed with pip:

{
  "mcpServers": {
    "bht": {
      "command": "python",
      "args": ["-m", "bht_mcp"]
    }
  }
}

Claude Code

claude mcp add bht -- uvx bht-mcp

Or with pip:

claude mcp add bht -- python -m bht_mcp

Local LLMs (Open WebUI, llama.cpp, Ollama, etc.)

If your local LLM setup supports MCP, configure it to launch bht-mcp as a stdio subprocess:

With uv:

{
  "mcpServers": {
    "bht": {
      "command": "uvx",
      "args": ["bht-mcp"]
    }
  }
}

With pip:

{
  "mcpServers": {
    "bht": {
      "command": "python",
      "args": ["-m", "bht_mcp"]
    }
  }
}

Note: MCP tool calling requires a model that supports function/tool calling. Most 7B+ instruction-tuned models work (Llama 3, Mistral, Qwen, etc.).

Other MCP-compatible clients

Any client that supports MCP stdio transport can use bht-mcp. Use uvx bht-mcp or python -m bht_mcp as the server command.

After adding, restart your client. You should see 7 BHt tools available.


Research Scenarios

You don't need to know the tool names or parameters โ€” just describe what you want in natural language. The AI figures out which tools to call.

Read a verse

"Show me Genesis 1:1 word by word with grammatical analysis"

The AI finds all tokens in the verse, then retrieves morphology for each:

barฤ(สพ) โ€” Suffixkonjugation, 3rd person masc. singular, Qal stem, root BRสพ
สพรฏlล*hฤซm โ€” Substantiv, masc. plural, base สพl-h
สพศงt โ€” Praeposition
ha=ลกamaym โ€” Substantiv with article, masc. plural

Explore a root

"Find all forms of root สพMR (say/speak) in the Psalms"

The AI searches for all tokens with this root in the specified book and presents the results grouped by form.

Check manuscript variants

"Are there textual variants in Genesis 1?"

โ†’ Gen 1,7c โ€” "kin": differs in Greek (G); G adds 7c text
โ†’ Gen 1,9b โ€” "maqลm": G reads miqwวŸ, MT reads miqwฤ“-m?

Verbal stem distribution

"What verbal stems appear in Ecclesiastes, and how frequent are they?"

The AI searches for all verbs in Kohelet, retrieves their stem information, and presents frequency statistics:

โ†’ G (Qal): 312, D (Piel): 45, H (Hiphil): 67, N (Niphal): 28, ...

Compare sentence structure

"Compare the syntactic structure of Gen 1:1 and the opening of Isaiah 40:1"

The AI retrieves sentence-level analysis for both verses and highlights structural differences โ€” sentence type, syntagm patterns, and clause relationships.

Find rare verb forms

"Show me all Hophal (HP) passive verbs in the Torah"

The AI searches each Torah book for Hophal stems and compiles a comprehensive list across Genesis through Deuteronomy.

Identify Aramaic sections

"Which tokens in Daniel are marked as Aramaic rather than Hebrew?"

The AI discovers the language codes available in BHt, then filters Daniel's tokens by language โ€” revealing the Aramaic sections (chapters 2:4bโ€“7:28).

Hapax legomena search

"Find lexemes that appear only once in the Hebrew Bible"

The AI iterates through lexemes from a book, checking each one's frequency across the entire corpus. Lexemes with exactly one occurrence are flagged as hapax legomena.

Cross-book morphological comparison

"Compare the construct chain patterns (Constructus) between Proverbs and Job"

The AI searches both books for construct-state nouns, then compares frequency, lexeme variety, and syntactic positions to reveal stylistic differences.

Syntax tree comparison for parallel passages

"Compare the word-level syntax of Psalm 18 and 2 Samuel 22 (parallel texts)"

The AI retrieves syntactic trees for matching verses in both books and highlights structural divergences between the two textual traditions.

Ben Sira manuscript comparison

"Which chapters of Sirach are preserved in manuscript A vs manuscript B?"

The AI queries the book list to show manuscript coverage:

โ†’ ASir: chapters 2โ€“16,23,27 (17 chapters)
โ†’ BSir: chapters 10โ€“11,15โ€“16,20,30โ€“51 (26 chapters)
โ†’ Overlap: chapters 10,11,15,16 โ€” compare these

Tool Reference

Tool Purpose BHt Requests
bht_list_books List all 47 books with codes and chapter counts 0
bht_field_info Get valid values for any of 42 search fields 0โ€“1
bht_search Search tokens by location or morphological filters 0โ€“1
bht_token_detail Full morphological analysis of a single token 0โ€“1
bht_syntax_tree Word-level syntactic tree (Wortfรผgungsebene) 0โ€“2
bht_sentence_analysis Sentence-level analysis (Satzfรผgungsebene) 0โ€“2
bht_text_annotations Textual criticism annotations for a chapter 0โ€“1

Typical workflow: bht_list_books โ†’ bht_search โ†’ bht_token_detail โ†’ bht_syntax_tree

Every response includes a quota field showing daily usage:

{
  "data": [...],
  "quota": {"daily_html_used": 12, "daily_html_limit": 150, "daily_html_remaining": 138}
}

Rate Limits

This tool accesses a university research server. Built-in limits protect it:

Limit Value Reason
Request interval 1 req/s Server capacity protection
Daily HTML requests 150/day Token detail, syntax, sentence, annotation pages
Daily JSON requests Unlimited Search API is lightweight

These limits are comparable to a researcher manually browsing the site (typically 25โ€“100 pages/day). The daily limit resets at midnight.

When the limit is reached, cached data remains fully accessible โ€” only new HTML fetches are blocked.


License

Code: MIT

BHt data: CC BY-SA 4.0 (LMU Munich)


๐Ÿ‡ฐ๐Ÿ‡ท ํ•œ๊ตญ์–ด

AI ์–ด์‹œ์Šคํ„ดํŠธ์—๊ฒŒ ํžˆ๋ธŒ๋ฆฌ์–ด ์„ฑ๊ฒฝ 489,000๊ฐœ ์ด์ƒ์˜ ํ˜•ํƒœ๋ก  ๋ถ„์„ ํ† ํฐ์„ ๊ฒ€์ƒ‰, ๋ถ„์„, ๋น„๊ตํ•˜๋„๋ก ์š”์ฒญํ•˜์„ธ์š” โ€” ์ฑ„ํŒ… ์ธํ„ฐํŽ˜์ด์Šค์—์„œ ๋ฐ”๋กœ.

์‚ฌ์šฉ์ž: "์ฐฝ์„ธ๊ธฐ์™€ ์ด์‚ฌ์•ผ์—์„œ ์–ด๊ทผ BRสพ(์ฐฝ์กฐํ•˜๋‹ค)์˜ ์‚ฌ์šฉ์„ ๋น„๊ตํ•ด์ค˜"
AI:    [๊ฐ ์ฑ…์—์„œ ์–ด๊ทผ ํ•„ํ„ฐ๋กœ bht_search๋ฅผ ํ˜ธ์ถœํ•˜๊ณ , ์„ ํƒ๋œ ํ† ํฐ์— ๋Œ€ํ•ด
        bht_token_detail์„ ํ˜ธ์ถœ โ€” ๋‘ ์ฑ…์˜ ํ˜•ํƒœ๋ก  ๋ถ„์„, ๋™์‚ฌ ์–ด๊ฐ„,
        ํ†ต์‚ฌ์  ๋งฅ๋ฝ์„ ๋ฐ˜ํ™˜ํ•ฉ๋‹ˆ๋‹ค]

ํžˆ๋ธŒ๋ฆฌ์–ด ์ „๋ฌธ ์ง€์‹ ์—†์ด๋„ ์‹œ์ž‘ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. AI๊ฐ€ ์–ธ์–ดํ•™ ๋ฐ์ดํ„ฐ๋ฅผ ์ฝ๊ณ  ์„ค๋ช…ํ•ด์ค๋‹ˆ๋‹ค.


BHt ์†Œ๊ฐœ

BHt (Biblia Hebraica transcripta)๋Š” ๋ฎŒํ—จ ๋Œ€ํ•™๊ต(LMU Munich)์—์„œ Wolfgang Richter ๊ต์ˆ˜์˜ ์ง€๋„ ์•„๋ž˜ ๊ด€๋ฆฌ๋˜๋Š” ํžˆ๋ธŒ๋ฆฌ์–ด ์„ฑ๊ฒฝ ๋””์ง€ํ„ธ ์ „์‚ฌ๋ณธ์ž…๋‹ˆ๋‹ค.

  • 489,437๊ฐœ ํ† ํฐ โ€” ์™„์ „ํ•œ ํ˜•ํƒœ๋ก  ๋ถ„์„ ํฌํ•จ
  • Richter ์ „์‚ฌ ์ฒด๊ณ„ โ€” ๋ผํ‹ด ๋ฌธ์ž ๊ธฐ๋ฐ˜ ์Œ์†Œ ํ‘œ๊ธฐ (์˜ˆ: barฤ(สพ) = ื‘ึธึผืจึธื)
  • 5๋ถ„๋ฅ˜ ํ’ˆ์‚ฌ ์ฒด๊ณ„ (Hauptwortart, Nebenwortart, Fรผgwortart ๋“ฑ)
  • ํ†ต์‚ฌ ํŠธ๋ฆฌ โ€” ๋‹จ์–ด ์ˆ˜์ค€(Wortfรผgungsebene) ๋ฐ ๋ฌธ์žฅ ์ˆ˜์ค€(Satzfรผgungsebene)
  • ํ…์ŠคํŠธ ๋น„ํ‰ ์ฃผ์„ โ€” ๊ทธ๋ฆฌ์Šค์–ด/๋งˆ์†Œ๋ผ ์‚ฌ๋ณธ ์ด๋ณธ ๋ฐ์ดํ„ฐ
  • ์‹œ๋ผํฌ ์‚ฌ๋ณธ ๋‹จํŽธ 8์ข… (๋ฒค ์‹œ๋ผ, ์นด์ด๋กœ ๊ฒŒ๋‹ˆ์ž ๋ฐ ๋งˆ์‚ฌ๋‹ค ์ถœํ† )

์ž‘๋™ ๋ฐฉ์‹

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”  stdio  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”  cache miss  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚  MCP Client  โ”‚ โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ†’โ”‚  bht-mcp         โ”‚ โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ†’โ”‚  BHt Website โ”‚
โ”‚  (Claude,    โ”‚ โ†โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”‚  (local process) โ”‚ โ†โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”‚ (LMU Munich) โ”‚
โ”‚  local LLM,  โ”‚         โ”‚  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”  โ”‚              โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
โ”‚  etc.)       โ”‚         โ”‚  โ”‚ ~/.bht/    โ”‚  โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜         โ”‚  โ”‚ cache.db   โ”‚  โ”‚  โ† local SQLite cache
                         โ”‚  โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜  โ”‚
                         โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
  • ์™„์ „ํžˆ ๋กœ์ปฌ์—์„œ ์‹คํ–‰๋ฉ๋‹ˆ๋‹ค. ์›๊ฒฉ ์„œ๋ฒ„ ์—†์Œ, API ํ‚ค ์—†์Œ, ๋น„์šฉ ์—†์Œ.
  • ์ ์ง„์  ์บ์‹ฑ. ํŠน์ • ์ฑ…์„ ์ฒ˜์Œ ๊ฒ€์ƒ‰ํ•˜๋ฉด ํ•ด๋‹น ์ฑ…์˜ ์ „์ฒด ํ† ํฐ์„ 1ํšŒ ์š”์ฒญ์œผ๋กœ ๊ฐ€์ ธ์˜ต๋‹ˆ๋‹ค. ์ดํ›„ ๊ฐ™์€ ์ฑ…์˜ ๊ฒ€์ƒ‰์€ ์ฆ‰์‹œ โ€” ๋„คํŠธ์›Œํฌ ์š”์ฒญ 0ํšŒ.
  • ์„œ๋ฒ„ ๋ณดํ˜ธ. ๋‚ด์žฅ ์†๋„ ์ œํ•œ(์ดˆ๋‹น 1์š”์ฒญ, ์ผ์ผ HTML 150๊ฑด)์ด ๋Œ€ํ•™ ์„œ๋ฒ„๋ฅผ ๋ณดํ˜ธํ•ฉ๋‹ˆ๋‹ค. ๋Œ€๋Ÿ‰ ์Šคํฌ๋ž˜ํ•‘์„ ํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.

์„ค์น˜ ๋ฐ ์„ค์ •

๋ฐฉ๋ฒ• A: uv ์‚ฌ์šฉ (๊ถŒ์žฅ)

uv๋Š” MCP ์„œ๋ฒ„ ์‹คํ–‰์˜ ํ‘œ์ค€ ๋„๊ตฌ์ž…๋‹ˆ๋‹ค. ๋ณ„๋„ ์„ค์น˜ ๋‹จ๊ณ„ ์—†์ด ํด๋ผ์ด์–ธํŠธ ์„ค์ •๋งŒ ํ•˜๋ฉด ๋ฉ๋‹ˆ๋‹ค.

uv ์„ค์น˜ (์ตœ์ดˆ 1ํšŒ):

ํ”Œ๋žซํผ ๋ฐฉ๋ฒ•
macOS brew install uv
Windows powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
Linux curl -LsSf https://astral.sh/uv/install.sh | sh

์„ค์น˜ ํ›„ ์•„๋ž˜ MCP ํด๋ผ์ด์–ธํŠธ ์„ค์ •์œผ๋กœ ๋ฐ”๋กœ ์ง„ํ–‰ํ•˜์„ธ์š”.

๋ฐฉ๋ฒ• B: pip ์‚ฌ์šฉ

์ „ํ†ต์ ์ธ ๋ฐฉ์‹์„ ์„ ํ˜ธํ•˜๋Š” ๊ฒฝ์šฐ:

pip install bht-mcp

Python 3.11 ์ด์ƒ ํ•„์š”. Python์ด ์—†๋Š” ๊ฒฝ์šฐ: python.org/downloads (Windows: "Add Python to PATH" ์ฒดํฌ). macOS: brew install python. Linux: sudo apt install python3 python3-pip.


MCP ํด๋ผ์ด์–ธํŠธ ์„ค์ •

MCP (Model Context Protocol)๋Š” AI ์–ด์‹œ์Šคํ„ดํŠธ๊ฐ€ ์™ธ๋ถ€ ๋„๊ตฌ๋ฅผ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๊ฒŒ ํ•ด์ค๋‹ˆ๋‹ค. ์•„๋ž˜์—์„œ ์‚ฌ์šฉ ์ค‘์ธ ํด๋ผ์ด์–ธํŠธ๋ฅผ ์„ ํƒํ•˜์„ธ์š”:

Claude Desktop

MCP ์„ค์ •์„ ํŽธ์ง‘ํ•ฉ๋‹ˆ๋‹ค (Settings โ†’ Developer โ†’ MCP Servers):

uv๋กœ ์„ค์น˜ํ•œ ๊ฒฝ์šฐ:

{
  "mcpServers": {
    "bht": {
      "command": "uvx",
      "args": ["bht-mcp"]
    }
  }
}

pip์œผ๋กœ ์„ค์น˜ํ•œ ๊ฒฝ์šฐ:

{
  "mcpServers": {
    "bht": {
      "command": "python",
      "args": ["-m", "bht_mcp"]
    }
  }
}

Claude Code

claude mcp add bht -- uvx bht-mcp

pip ์‚ฌ์šฉ ์‹œ:

claude mcp add bht -- python -m bht_mcp

๋กœ์ปฌ LLM (Open WebUI, llama.cpp, Ollama ๋“ฑ)

๋กœ์ปฌ LLM ํ™˜๊ฒฝ์ด MCP๋ฅผ ์ง€์›ํ•˜๋Š” ๊ฒฝ์šฐ, bht-mcp๋ฅผ stdio ์„œ๋ธŒํ”„๋กœ์„ธ์Šค๋กœ ์„ค์ •ํ•˜์„ธ์š”:

uv ์‚ฌ์šฉ:

{
  "mcpServers": {
    "bht": {
      "command": "uvx",
      "args": ["bht-mcp"]
    }
  }
}

pip ์‚ฌ์šฉ:

{
  "mcpServers": {
    "bht": {
      "command": "python",
      "args": ["-m", "bht_mcp"]
    }
  }
}

์ฐธ๊ณ : MCP tool calling์„ ์‚ฌ์šฉํ•˜๋ ค๋ฉด ํ•จ์ˆ˜/๋„๊ตฌ ํ˜ธ์ถœ์„ ์ง€์›ํ•˜๋Š” ๋ชจ๋ธ์ด ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค. ๋Œ€๋ถ€๋ถ„์˜ 7B+ instruction-tuned ๋ชจ๋ธ์ด ๋™์ž‘ํ•ฉ๋‹ˆ๋‹ค (Llama 3, Mistral, Qwen ๋“ฑ).

๊ธฐํƒ€ MCP ํ˜ธํ™˜ ํด๋ผ์ด์–ธํŠธ

MCP stdio ์ „์†ก์„ ์ง€์›ํ•˜๋Š” ๋ชจ๋“  ํด๋ผ์ด์–ธํŠธ์—์„œ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์„œ๋ฒ„ ๋ช…๋ น์–ด๋Š” uvx bht-mcp ๋˜๋Š” python -m bht_mcp์ž…๋‹ˆ๋‹ค.

์ถ”๊ฐ€ ํ›„ ํด๋ผ์ด์–ธํŠธ๋ฅผ ์žฌ์‹œ์ž‘ํ•˜๋ฉด 7๊ฐœ์˜ BHt ๋„๊ตฌ๊ฐ€ ํ™œ์„ฑํ™”๋ฉ๋‹ˆ๋‹ค.


์—ฐ๊ตฌ ์‹œ๋‚˜๋ฆฌ์˜ค

๋„๊ตฌ ์ด๋ฆ„์ด๋‚˜ ํŒŒ๋ผ๋ฏธํ„ฐ๋ฅผ ์•Œ ํ•„์š” ์—†์Šต๋‹ˆ๋‹ค โ€” ์›ํ•˜๋Š” ๊ฒƒ์„ ์ž์—ฐ์–ด๋กœ ์„ค๋ช…ํ•˜๋ฉด AI๊ฐ€ ์ ์ ˆํ•œ ๋„๊ตฌ๋ฅผ ํ˜ธ์ถœํ•ฉ๋‹ˆ๋‹ค.

๊ตฌ์ ˆ ๋ถ„์„

"์ฐฝ์„ธ๊ธฐ 1:1์„ ๋‹จ์–ด๋ณ„๋กœ ๋ฌธ๋ฒ• ๋ถ„์„๊ณผ ํ•จ๊ป˜ ๋ณด์—ฌ์ฃผ์„ธ์š”"

AI๊ฐ€ ํ•ด๋‹น ์ ˆ์˜ ๋ชจ๋“  ํ† ํฐ์„ ์ฐพ๊ณ , ๊ฐ๊ฐ์˜ ํ˜•ํƒœ๋ก ์„ ์กฐํšŒํ•ฉ๋‹ˆ๋‹ค:

barฤ(สพ) โ€” Suffixkonjugation, ๋‚จ์„ฑ ๋‹จ์ˆ˜ 3์ธ์นญ, ์นผ(Qal) ์–ด๊ฐ„, ์–ด๊ทผ BRสพ
สพรฏlล*hฤซm โ€” Substantiv, ๋‚จ์„ฑ ๋ณต์ˆ˜, ๊ธฐ์ดˆํ˜• สพl-h
สพศงt โ€” ์ „์น˜์‚ฌ(Praeposition)
ha=ลกamaym โ€” ๊ด€์‚ฌ ํฌํ•จ Substantiv, ๋‚จ์„ฑ ๋ณต์ˆ˜

์–ด๊ทผ ํƒ์ƒ‰

"์‹œํŽธ์—์„œ ์–ด๊ทผ สพMR (๋งํ•˜๋‹ค)์˜ ๋ชจ๋“  ํ˜•ํƒœ๋ฅผ ์ฐพ์•„์ฃผ์„ธ์š”"

AI๊ฐ€ ํ•ด๋‹น ์ฑ…์—์„œ ์ด ์–ด๊ทผ์˜ ๋ชจ๋“  ํ† ํฐ์„ ๊ฒ€์ƒ‰ํ•˜๊ณ , ํ˜•ํƒœ๋ณ„๋กœ ๊ทธ๋ฃนํ™”ํ•˜์—ฌ ๊ฒฐ๊ณผ๋ฅผ ์ œ์‹œํ•ฉ๋‹ˆ๋‹ค.

์‚ฌ๋ณธ ์ด๋ณธ ํ™•์ธ

"์ฐฝ์„ธ๊ธฐ 1์žฅ์— ํ…์ŠคํŠธ ๋น„ํ‰ ์ฃผ์„์ด ์žˆ๋‚˜์š”?"

โ†’ Gen 1,7c โ€” "kin": ๊ทธ๋ฆฌ์Šค์–ด(G)์™€ ์ฐจ์ด; G์— 7c ํ…์ŠคํŠธ ์ถ”๊ฐ€
โ†’ Gen 1,9b โ€” "maqลm": G๋Š” miqwวŸ, MT๋Š” miqwฤ“-m?

๋™์‚ฌ ์–ด๊ฐ„ ๋ถ„ํฌ ๋ถ„์„

"์ „๋„์„œ์— ์–ด๋–ค ๋™์‚ฌ ์–ด๊ฐ„์ด ๋‚˜ํƒ€๋‚˜๋ฉฐ, ๋นˆ๋„๋Š” ์–ด๋–ค๊ฐ€์š”?"

AI๊ฐ€ ์ฝ”ํ—ฌ๋ ›์˜ ๋ชจ๋“  ๋™์‚ฌ๋ฅผ ๊ฒ€์ƒ‰ํ•˜๊ณ , ์–ด๊ฐ„ ์ •๋ณด๋ฅผ ์กฐํšŒํ•˜์—ฌ ๋นˆ๋„ ํ†ต๊ณ„๋ฅผ ์ œ์‹œํ•ฉ๋‹ˆ๋‹ค:

โ†’ G (์นผ/Qal): 312, D (ํ”ผ์—˜/Piel): 45, H (ํžˆํ•„/Hiphil): 67, N (๋‹ˆํŒ”/Niphal): 28, ...

์ฑ… ๊ฐ„ ๋ฌธ์žฅ ๊ตฌ์กฐ ๋น„๊ต

"์ฐฝ์„ธ๊ธฐ 1:1๊ณผ ์ด์‚ฌ์•ผ 40:1์˜ ํ†ต์‚ฌ ๊ตฌ์กฐ๋ฅผ ๋น„๊ตํ•ด์ฃผ์„ธ์š”"

AI๊ฐ€ ๋‘ ๊ตฌ์ ˆ์˜ ๋ฌธ์žฅ ์ˆ˜์ค€ ๋ถ„์„์„ ๊ฐ€์ ธ์™€ ๊ตฌ์กฐ์  ์ฐจ์ด๋ฅผ ๊ฐ•์กฐํ•ฉ๋‹ˆ๋‹ค โ€” ๋ฌธ์žฅ ์œ ํ˜•, ํ†ตํ•ฉ์†Œ(Syntagmen) ํŒจํ„ด, ์ ˆ ๊ด€๊ณ„.

ํฌ๊ท€ ๋™์‚ฌํ˜• ํƒ์ƒ‰

"ํ† ๋ผ์—์„œ ํ˜ธํŒ”(Hophal, HP) ์ˆ˜๋™ํƒœ ๋™์‚ฌ๋ฅผ ๋ชจ๋‘ ์ฐพ์•„์ฃผ์„ธ์š”"

AI๊ฐ€ ์ฐฝ์„ธ๊ธฐ๋ถ€ํ„ฐ ์‹ ๋ช…๊ธฐ๊นŒ์ง€ ๊ฐ ํ† ๋ผ ์ฑ…์—์„œ ํ˜ธํŒ” ์–ด๊ฐ„์„ ๊ฒ€์ƒ‰ํ•˜๊ณ  ์ข…ํ•ฉ ๋ชฉ๋ก์„ ์ž‘์„ฑํ•ฉ๋‹ˆ๋‹ค.

์•„๋žŒ์–ด ๊ตฌ๊ฐ„ ์‹๋ณ„

"๋‹ค๋‹ˆ์—˜์„œ์—์„œ ํžˆ๋ธŒ๋ฆฌ์–ด๊ฐ€ ์•„๋‹Œ ์•„๋žŒ์–ด๋กœ ํ‘œ์‹œ๋œ ํ† ํฐ์€?"

AI๊ฐ€ BHt์—์„œ ์‚ฌ์šฉ ๊ฐ€๋Šฅํ•œ ์–ธ์–ด ์ฝ”๋“œ๋ฅผ ๋ฐœ๊ฒฌํ•œ ํ›„, ๋‹ค๋‹ˆ์—˜์„œ์˜ ํ† ํฐ์„ ์–ธ์–ด๋ณ„๋กœ ํ•„ํ„ฐ๋งํ•ฉ๋‹ˆ๋‹ค โ€” ์•„๋žŒ์–ด ๊ตฌ๊ฐ„(2:4bโ€“7:28์žฅ)์ด ๋“œ๋Ÿฌ๋‚ฉ๋‹ˆ๋‹ค.

ํ•˜ํŒ์Šค ๋ ˆ๊ณ ๋ฉ”๋…ผ(Hapax legomenon) ํƒ์ƒ‰

"ํžˆ๋ธŒ๋ฆฌ์–ด ์„ฑ๊ฒฝ์—์„œ ๋‹จ ํ•œ ๋ฒˆ๋งŒ ๋“ฑ์žฅํ•˜๋Š” ์–ดํœ˜์†Œ๋ฅผ ์ฐพ์•„์ฃผ์„ธ์š”"

AI๊ฐ€ ํŠน์ • ์ฑ…์˜ ์–ดํœ˜์†Œ๋ฅผ ์ˆœํšŒํ•˜๋ฉฐ ์ „์ฒด ์ฝ”ํผ์Šค์—์„œ ๊ฐ๊ฐ์˜ ๋นˆ๋„๋ฅผ ํ™•์ธํ•ฉ๋‹ˆ๋‹ค. ์ •ํ™•ํžˆ 1ํšŒ ์ถœํ˜„ํ•˜๋Š” ์–ดํœ˜์†Œ๊ฐ€ ํ•˜ํŒ์Šค ๋ ˆ๊ณ ๋ฉ”๋…ผ์œผ๋กœ ํ‘œ์‹œ๋ฉ๋‹ˆ๋‹ค.

์ฑ… ๊ฐ„ ํ˜•ํƒœ๋ก  ๋น„๊ต

"์ž ์–ธ๊ณผ ์šฅ๊ธฐ์˜ ์—ฐ๊ณ„ํ˜•(Constructus) ํŒจํ„ด์„ ๋น„๊ตํ•ด์ฃผ์„ธ์š”"

AI๊ฐ€ ๋‘ ์ฑ…์—์„œ ์—ฐ๊ณ„ํ˜• ๋ช…์‚ฌ๋ฅผ ๊ฒ€์ƒ‰ํ•œ ํ›„, ๋นˆ๋„, ์–ดํœ˜์†Œ ๋‹ค์–‘์„ฑ, ํ†ต์‚ฌ์  ์œ„์น˜๋ฅผ ๋น„๊ตํ•˜์—ฌ ๋ฌธ์ฒด์  ์ฐจ์ด๋ฅผ ๋“œ๋Ÿฌ๋ƒ…๋‹ˆ๋‹ค.

๋ณ‘ํ–‰ ๋ณธ๋ฌธ์˜ ํ†ต์‚ฌ ํŠธ๋ฆฌ ๋น„๊ต

"์‹œํŽธ 18ํŽธ๊ณผ ์‚ฌ๋ฌด์—˜ํ•˜ 22์žฅ์˜ ๋‹จ์–ด ์ˆ˜์ค€ ํ†ต์‚ฌ ๊ตฌ์กฐ๋ฅผ ๋น„๊ตํ•ด์ฃผ์„ธ์š” (๋ณ‘ํ–‰ ๋ณธ๋ฌธ)"

AI๊ฐ€ ๋‘ ์ฑ…์˜ ๋Œ€์‘ ์ ˆ์—์„œ ํ†ต์‚ฌ ํŠธ๋ฆฌ๋ฅผ ๊ฐ€์ ธ์™€ ๋‘ ํ…์ŠคํŠธ ์ „์Šน ์‚ฌ์ด์˜ ๊ตฌ์กฐ์  ์ฐจ์ด๋ฅผ ๊ฐ•์กฐํ•ฉ๋‹ˆ๋‹ค.

๋ฒค ์‹œ๋ผ ์‚ฌ๋ณธ ๋น„๊ต

"์‹œ๋ผํฌ ์‚ฌ๋ณธ A์™€ ์‚ฌ๋ณธ B์— ๋ณด์กด๋œ ์žฅ์€ ๊ฐ๊ฐ ์–ด๋–ค ๊ฒƒ์ธ๊ฐ€์š”?"

AI๊ฐ€ ์ฑ… ๋ชฉ๋ก์„ ์กฐํšŒํ•˜์—ฌ ์‚ฌ๋ณธ ์ปค๋ฒ„๋ฆฌ์ง€๋ฅผ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค:

โ†’ ASir: 2โ€“16, 23, 27์žฅ (17๊ฐœ ์žฅ)
โ†’ BSir: 10โ€“11, 15โ€“16, 20, 30โ€“51์žฅ (26๊ฐœ ์žฅ)
โ†’ ๊ฒน์น˜๋Š” ์žฅ: 10, 11, 15, 16 โ€” ์ด๋“ค์„ ๋น„๊ต

๋„๊ตฌ ์ฐธ์กฐ

๋„๊ตฌ ์šฉ๋„ BHt ์š”์ฒญ ์ˆ˜
bht_list_books 47๊ฐœ ์ฑ… ๋ชฉ๋ก (์ฝ”๋“œ์™€ ์žฅ ์ˆ˜ ํฌํ•จ) 0
bht_field_info 42๊ฐœ ๊ฒ€์ƒ‰ ํ•„๋“œ์˜ ์œ ํšจํ•œ ๊ฐ’ ์กฐํšŒ 0โ€“1
bht_search ์œ„์น˜ ๋˜๋Š” ํ˜•ํƒœ๋ก  ํ•„ํ„ฐ๋กœ ํ† ํฐ ๊ฒ€์ƒ‰ 0โ€“1
bht_token_detail ๋‹จ์ผ ํ† ํฐ์˜ ์™„์ „ํ•œ ํ˜•ํƒœ๋ก  ๋ถ„์„ 0โ€“1
bht_syntax_tree ๋‹จ์–ด ์ˆ˜์ค€ ํ†ต์‚ฌ ํŠธ๋ฆฌ (Wortfรผgungsebene) 0โ€“2
bht_sentence_analysis ๋ฌธ์žฅ ์ˆ˜์ค€ ๋ถ„์„ (Satzfรผgungsebene) 0โ€“2
bht_text_annotations ์žฅ ๋‹จ์œ„ ํ…์ŠคํŠธ ๋น„ํ‰ ์ฃผ์„ 0โ€“1

์ผ๋ฐ˜์ ์ธ ์›Œํฌํ”Œ๋กœ์šฐ: bht_list_books โ†’ bht_search โ†’ bht_token_detail โ†’ bht_syntax_tree

๋ชจ๋“  ์‘๋‹ต์— ์ผ์ผ ์‚ฌ์šฉ๋Ÿ‰์„ ๋ณด์—ฌ์ฃผ๋Š” quota ํ•„๋“œ๊ฐ€ ํฌํ•จ๋ฉ๋‹ˆ๋‹ค:

{
  "data": [...],
  "quota": {"daily_html_used": 12, "daily_html_limit": 150, "daily_html_remaining": 138}
}

์‚ฌ์šฉ ์ œํ•œ

์ด ๋„๊ตฌ๋Š” ๋Œ€ํ•™ ์—ฐ๊ตฌ ์„œ๋ฒ„์— ์ ‘๊ทผํ•ฉ๋‹ˆ๋‹ค. ๋‚ด์žฅ๋œ ์ œํ•œ์ด ์„œ๋ฒ„๋ฅผ ๋ณดํ˜ธํ•ฉ๋‹ˆ๋‹ค:

์ œํ•œ ๊ฐ’ ์ด์œ 
์š”์ฒญ ๊ฐ„๊ฒฉ ์ดˆ๋‹น 1ํšŒ ์„œ๋ฒ„ ์šฉ๋Ÿ‰ ๋ณดํ˜ธ
์ผ์ผ HTML ์š”์ฒญ 150๊ฑด/์ผ ํ† ํฐ ์ƒ์„ธ, ํ†ต์‚ฌ, ๋ฌธ์žฅ, ์ฃผ์„ ํŽ˜์ด์ง€
์ผ์ผ JSON ์š”์ฒญ ๋ฌด์ œํ•œ ๊ฒ€์ƒ‰ API๋Š” ๊ฒฝ๋Ÿ‰

์ด ์ œํ•œ์€ ์—ฐ๊ตฌ์ž๊ฐ€ ์ง์ ‘ ์‚ฌ์ดํŠธ๋ฅผ ํƒ์ƒ‰ํ•˜๋Š” ์ˆ˜์ค€(๋ณดํ†ต ํ•˜๋ฃจ 25โ€“100 ํŽ˜์ด์ง€)๊ณผ ๋™๋“ฑํ•ฉ๋‹ˆ๋‹ค. ์ผ์ผ ์ œํ•œ์€ ์ž์ •์— ์ดˆ๊ธฐํ™”๋ฉ๋‹ˆ๋‹ค.

์ œํ•œ์— ๋„๋‹ฌํ•˜๋ฉด ์บ์‹œ๋œ ๋ฐ์ดํ„ฐ๋Š” ์—ฌ์ „ํžˆ ์™„์ „ํžˆ ์ ‘๊ทผ ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค โ€” ์ƒˆ๋กœ์šด HTML ๊ฐ€์ ธ์˜ค๊ธฐ๋งŒ ์ฐจ๋‹จ๋ฉ๋‹ˆ๋‹ค.


๋ผ์ด์„ ์Šค

์ฝ”๋“œ: MIT

BHt ๋ฐ์ดํ„ฐ: CC BY-SA 4.0 (LMU Munich)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

bht_mcp-0.1.3.tar.gz (33.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

bht_mcp-0.1.3-py3-none-any.whl (40.3 kB view details)

Uploaded Python 3

File details

Details for the file bht_mcp-0.1.3.tar.gz.

File metadata

  • Download URL: bht_mcp-0.1.3.tar.gz
  • Upload date:
  • Size: 33.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.3

File hashes

Hashes for bht_mcp-0.1.3.tar.gz
Algorithm Hash digest
SHA256 8f3f40fb76a9959d15b7712207076f2f8f9d35014414d9176ec9d5bf73bcfcde
MD5 258f086198d4d285b5be1cccca317105
BLAKE2b-256 d534753d613a0161d93b35c22a9739a7da74d25870ae830b810f6fa50cc9fa87

See more details on using hashes here.

File details

Details for the file bht_mcp-0.1.3-py3-none-any.whl.

File metadata

  • Download URL: bht_mcp-0.1.3-py3-none-any.whl
  • Upload date:
  • Size: 40.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.3

File hashes

Hashes for bht_mcp-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 a58c617daf458b9ab9631e054259bb9ff5888cb9d92ae5a2da90098e5b0543fd
MD5 b13a42ed6cf70d3e7197fe8537b781e1
BLAKE2b-256 5a0505f33aa0410ed90854f0f4352e0101f84a024b65b2a488e37a922b8afc97

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page