Skip to content
Back to search

studybible-mcp

Bible study MCP server with Greek/Hebrew lexicons and Fee & Stuart hermeneutics

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/djayatillake/studybible-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/djayatillake/studybible-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/djayatillake--studybible-mcp/badge.svg)](/listings/djayatillake--studybible-mcp)

HTML

<a href="/listings/djayatillake--studybible-mcp"><img src="/api/listings/djayatillake--studybible-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Claude Desktop

1. Open **Settings** → **Connectors** 2. Click **Add Custom Connector** 3. Paste: `https://studybible-mcp.fly.dev/sse` 4. Restart Claude Desktop

That's it. No signup, no API keys, no downloads.

Claude Code

claude mcp add study-bible https://studybible-mcp.fly.dev/sse

ChatGPT (Developer Mode)

1. Open **Settings** → **Developer Mode** → enable it 2. Go to **Actions** → **Add MCP Server** 3. Enter URL: `https://studybible-mcp.fly.dev/mcp`

Cursor / Windsurf / Cline

Add to your MCP configuration (usually `.cursor/mcp.json`, `.windsurf/mcp.json`, or Cline settings):

{
  "mcpServers": {
    "study-bible": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://studybible-mcp.fly.dev/sse"]
    }
  }
}

Install via pip / uvx (local stdio)

pip install studybible-mcp
studybible-mcp --transport stdio

Or run directly without installing:

uvx studybible-mcp --transport stdio

Manual Config (Alternative)

If you prefer editing config files directly:

{
  "mcpServers": {
    "study-bible": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://studybible-mcp.fly.dev/sse"]
    }
  }
}

Config file locations: - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json` - Linux: `~/.config/Claude/claude_desktop_config.json`

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 1,596 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Study Bible MCP Server
  2. A Bible study assistant for Claude that provides full scholarly lexicons (LSJ Greek, BDB Hebrew, Abbott-Smith NT Greek), morphologically-tagged biblical texts, cross-references, Theographic genealogy graphs, Aquifer Open Study Notes, a Bible dictionary, key theological terms, Ancient Near East cultural context, and hermeneutical methodology based on Fee & Stuart's "How to Read the Bible for All Its Worth".
  3. ## Quick Start
  4. ### Claude Desktop
  5. 1. Open **Settings** → **Connectors**
  6. 2. Click **Add Custom Connector**
  7. 3. Paste: `https://studybible-mcp.fly.dev/mcp/`
  8. 4. Restart Claude Desktop
  9. That's it. No signup, no API keys, no downloads.
  10. ### Claude Code
  11. ```bash
  12. claude mcp add --transport http study-bible https://studybible-mcp.fly.dev/mcp/
  13. ```
  14. ### ChatGPT (Developer Mode)
  15. 1. Open **Settings** → **Developer Mode** → enable it
  16. 2. Go to **Actions** → **Add MCP Server**
  17. 3. Enter URL: `https://studybible-mcp.fly.dev/mcp/`
  18. ### Cursor / Windsurf / Cline
  19. Add to your MCP configuration (usually `.cursor/mcp.json`, `.windsurf/mcp.json`, or Cline settings):
  20. ```json
  21. {
  22. "mcpServers": {
  23. "study-bible": {
  24. "command": "npx",
  25. "args": ["-y", "mcp-remote", "https://studybible-mcp.fly.dev/mcp/"]
  26. }
  27. }
  28. }
  29. ```
  30. ### Install via pip / uvx (local stdio)
  31. ```bash
  32. pip install studybible-mcp
  33. studybible-mcp --transport stdio
  34. ```
  35. Or run directly without installing:
  36. ```bash
  37. uvx studybible-mcp --transport stdio
  38. ```
  39. ### Manual Config (Alternative)
  40. If you prefer editing config files directly:
  41. ```json
  42. {
  43. "mcpServers": {
  44. "study-bible": {
  45. "command": "npx",
  46. "args": ["-y", "mcp-remote", "https://studybible-mcp.fly.dev/mcp/"]
  47. }
  48. }
  49. }
  50. ```
  51. Config file locations:
  52. - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
  53. - Windows: `%APPDATA%\Claude\claude_desktop_config.json`
  54. - Linux: `~/.config/Claude/claude_desktop_config.json`
  55. ### Transports
  56. | Endpoint | Transport | Status |
  57. |----------|-----------|--------|
  58. | `https://studybible-mcp.fly.dev/mcp/` | Streamable HTTP (stateless; `/mcp` without the slash works too) | **Recommended** |
  59. | `https://studybible-mcp.fly.dev/sse` (+ `/messages`) | Legacy HTTP+SSE | **Deprecated**: still served for existing connectors, but will be removed. Re-add the connector with the `/mcp/` URL. |
  60. | `studybible-mcp --transport stdio` | stdio (local) | Supported |
  61. ---
  62. ## How It Works
  63. ### Architecture Overview
  64. ```
  65. ┌─────────────────────┐ ┌──────────────────────────────────────────┐
  66. │ Claude Desktop │ │ Study Bible MCP Server │
  67. │ or Claude Code │ │ (Fly.io) │
  68. │ │ │ │
  69. │ ┌───────────────┐ │ MCP │ ┌─────────────┐ ┌───────────────────┐ │
  70. │ │ User asks a │──┼─────┼─▶│ MCP Server │─▶│ SQLite DB (600+MB)│ │
  71. │ │ Bible question│ │ │ │ (Python) │ │ │ │
  72. │ └───────────────┘ │ │ └─────────────┘ │ • Lexicons (LSJ, │ │
  73. │ │ │ │ │ BDB, Abbott- │ │
  74. │ ┌───────────────┐ │ │ ▼ │ Smith, Strong's) │ │
  75. │ │ Claude uses │◀─┼─────┼── Tool Results │ • Tagged NT + OT │ │
  76. │ │ study tools to│ │ │ │ • Names + ACAI │ │
  77. │ │ answer │ │ │ │ • Morphology │ │
  78. │ └───────────────┘ │ │ │ • Study Notes │ │
  79. │ │ │ │ • Bible Dictionary │ │
  80. │ │ │ │ • Key Terms │ │
  81. │ │ │ │ • ANE Context │ │
  82. │ │ │ │ • Embeddings │ │
  83. │ │ │ └───────────────────┘ │
  84. └─────────────────────┘ └──────────────────────────────────────────┘
  85. ```
  86. When you ask Claude a Bible question:
  87. 1. Claude analyses your question and decides which tools to use
  88. 2. Claude calls the appropriate MCP tools (e.g., `lookup_verse`, `word_study`, `get_study_notes`)
  89. 3. The server queries the pre-built SQLite database
  90. 4. Results are returned to Claude
  91. 5. Claude synthesises the data into a helpful response
  92. See [ARCHITECTURE.md](ARCHITECTURE.md) for a full Mermaid flowchart of the available tools and how the agent chains them together.
  93. ### The Database
  94. The server includes a pre-built SQLite database (~600MB) containing:
  95. | Table | Rows | Content |
  96. |-------|------|---------|
  97. | `lexicon` | 19,391 | Greek (Full LSJ + Abbott-Smith NT) and Hebrew (Full BDB) word definitions with Strong's numbers |
  98. | `verses` | 31,280 | Every verse of the Bible with morphology tags |
  99. | `bsb_verses` | 31,086 | Berean Standard Bible text, the English the verse tools show |
  100. | `passages` | 5,290 | Verses grouped by ancient section markers |
  101. | `names` | 4,299 | Biblical people, places, and things |
  102. | `morphology` | 2,768 | Grammatical parsing code definitions |
  103. | `thematic_references` | 22 | Core theological theme cross-references |
  104. | `aquifer_content` | 102,673 | Study notes, dictionary articles, translation notes, key terms |
  105. | `acai_entities` | 6,019 | Rich entity annotations (people, places, groups, key terms) |
  106. | `ane_entries` | 87 | Ancient Near East cultural context entries across 12 dimensions |
  107. | `ane_book_mappings` | 314 | Maps ANE entries to biblical books and chapter ranges |
  108. | `torah_weave_units` | 86 | Moshe Kline's Torah Weave literary units (dataset version 1.1) |
  109. | `torah_weave_cells` | 1,019 | Their cells and subdivisions, with Hebrew-numbered verse ranges |
  110. | `verse_vectors` | 31,280 | OpenAI embeddings for semantic search |
  111. | `passage_vectors` | 5,190 | OpenAI embeddings for passage similarity |
  112. ---
  113. You can download the pre-built database directly: **[study_bible.db](https://studybible-mcp.fly.dev/download/study_bible.db)** (~750MB)
  114. The database includes CC BY-NC 4.0 material (the ETCBC Dead Sea Scrolls
  115. transcription and the Metsudah Chumash English), for non-commercial use only,
  116. and CC BY-SA 4.0 material (Perseus Josephus, First1KGreek Philo, Latin
  117. Wikisource 4 Ezra), which must be shared alike. The download response repeats
  118. this in an `X-Data-License-Notice` header.
  119. ---
  120. ## Available Tools
  121. ### Core Text & Language
  122. #### 1. `lookup_verse`
  123. Retrieve a verse, verse range, or whole chapter with its original language text and word-by-word analysis.
  124. **When Claude uses it**: User asks about a specific verse or passage, wants to see the Greek or Hebrew text, or asks about specific words in a passage.
  125. **Accepted references**: a verse (`John 3:16`), a range within a chapter (`Luke 19:1-3`; an en dash also works), a cross-chapter range (`Luke 19:45-20:2`), or whole chapters (`Psalm 23`, `Psalm 23-24`). Single-chapter books (Obadiah, Philemon, 2 John, 3 John, Jude) may be cited by verse alone, as is conventional: `Jude 3` means `Jude 1:3` and a bare `Jude` means the whole book. This applies to every tool's `reference` argument. Verses are matched by English chapter/verse numbering, so Old Testament verses whose Hebrew numbering differs (e.g. `Psalm 40:6`, stored as `Psa.40.6(40.7)`) are found, and an English verse stored as several source rows returns all of them. A Psalm superscription, which is verse 1 in the Hebrew, is headed as such (`Psa.82 superscription (Hebrew Psa.82.1)`). A passage returns at most 50 verses; longer requests (e.g. `Psalm 119`) open with a note naming the reference that continues the passage. Unknown books, missing chapters or verses, and reversed ranges get a message saying what exists.
  126. **What it returns**: English text from the Berean Standard Bible (labelled `(BSB)` once per response; STEPBible's word-by-word gloss, marked `[gloss]`, stands in for the few verses the BSB lacks, such as Psalm superscriptions and Matthew 17:21), original Greek/Hebrew text, word-by-word breakdown with Strong's numbers, optional morphological parsing, and genre-specific interpretation guidance. Notes about cross-references, Torah Weave partners, and NT/OT LXX quotations appear once per lookup; for a passage they name a verse to pass to those single-verse tools.
  127. **Example**:
  128. ```
  129. User: "Look up Romans 8:28 with the Greek"
  130. Claude calls: lookup_verse(reference="Romans 8:28", include_original=true)
  131. Returns:
  132. - Verse text in English
  133. - Greek: πάντα συνεργεῖ εἰς ἀγαθόν...
  134. - Word analysis: συνεργεῖ (G4903) = "works together" [V-PAI-3S]
  135. - Genre guidance: "Epistles - What problem was being addressed?"
  136. ```
  137. #### `compare_biblical_versions`
  138. Compare the Masoretic Text and Septuagint with explicit per-verse provenance.
  139. Covers Old Testament and Septuagint books only. Rows that share a canonical
  140. (MT/English) reference appear under one header, while each row keeps its own
  141. edition reference, so Hebrew/Greek Psalm numbering and other mapped
  142. versification shifts stay visible. Psalm 82:6, for example, shows MT `Psa.82.6`
  143. and LXX `Psa.81.6`; Psalm 40:6 shows MT `Psa.40.7` (Hebrew numbering) and LXX
  144. `Psa.39.7`.
  145. ```text
  146. compare_biblical_versions(
  147. reference="Psalm 24:1", # also "Psalm 82:1-8", "Psalm 81:6-82:1", "Psalm 82"
  148. versions=["MT", "LXX"],
  149. numbering="canonical", # or "lxx" to read the reference in Greek numbering
  150. include_original=true,
  151. include_morphology=false
  152. )
  153. ```
  154. Each edition row names its version, edition, and edition reference (plus the
  155. versification mapping whenever it is not `identity`), then its original text and
  156. English. Licences, source URLs, translation labels, the verse-mapping credit, and
  157. the Brenton caveat are listed once in a closing **Sources** block rather than on
  158. every row. A call returns at most 10 verses; a longer range or chapter is cut
  159. there with a note naming the verse to continue from.
  160. - **MT** comes from the STEPBible TAHOT verses already in the database (Westminster
  161. Leningrad Codex). Its English is STEPBible word glosses (interlinear, not a
  162. translation).
  163. - **LXX** covers all 59 books of the Rahlfs source edition. Brenton's English is
  164. shown only for the recension Brenton translated (Theodotion for Daniel, Susanna
  165. and Bel; Vaticanus B for Joshua and Judges); Old Greek and Alexandrinus rows say
  166. the translation is not available for that edition.
  167. - **Brenton's English is not a translation of the Rahlfs text.** Brenton (1844)
  168. translated his own Greek edition, based chiefly on Codex Vaticanus, and his
  169. English sometimes departs even from that Greek. Every row with his English
  170. carries a note saying so. Each such verse is also compared with
  171. [Brenton's own Greek](https://ebible.org/details.php?id=grcbrent) after
  172. spelling noise is removed: accents, breathings, case, punctuation, elision,
  173. movable nu, itacism (ει/ι), doubled consonants, nasal assimilation, crasis,
  174. Hellenistic spellings (λήμψομαι/λήψομαι), word division (ἀνὰ μέσον/ἀναμέσον),
  175. name spellings, and one-letter keying errors in Brenton's digital text. Where
  176. his Greek still adds, lacks, substitutes, or reorders words, the row shows a
  177. warning, a difference summary, and Brenton's Greek as the text his English
  178. translates. Deuteronomy 32:43, for example, reports "word order differs (υἱοὶ
  179. ἄγγελοι)", and Psalm 40:6 reports "Brenton's Greek reads σῶμα for ὠτία".
  180. Differing verse divisions do not count as differences. 8,914 of the 23,684
  181. rows with Brenton's own English (38%) are flagged. Unflagged rows can still
  182. differ, because a Greek-to-Greek comparison cannot see where his English
  183. departs from his own Greek.
  184. - **Most Apocrypha English is the KJV, not Brenton's translation.** For 1
  185. Esdras, 1–2 Maccabees, Baruch, Bel, Judith, the Letter of Jeremiah, Sirach,
  186. Susanna, Tobit, Wisdom, and Daniel 3:24–90 (the Prayer of Azariah and Song of
  187. the Three), Brenton's edition prints the KJV (Authorized Version) Apocrypha,
  188. lightly adapted by Brenton (verse-by-verse similarity to the KJV is 92–100%,
  189. against 24–49% for his own Hebrew-canon translations). The KJV was translated
  190. from other Greek texts, so it can contain words neither the Rahlfs nor
  191. Brenton's Greek has: Sirach 17:17 adds "in the division of the nations of the
  192. whole earth". These 4,630 rows label the English "KJV Apocrypha", are named in
  193. the Sources block with one closing note, and are not compared with Brenton's
  194. Greek. Greek Esther and 3–4 Maccabees are Brenton's own translation.
  195. - **Apocrypha rows are marked.** Rows outside the 66-book Protestant canon (the
  196. Septuagint-only books, the Greek additions to Esther, Daniel 3:24–90, Psalm
  197. 151, and Odes 7–8, 12 and 14) end their header with "(Apocrypha)", and the
  198. closing block adds one line saying they are not in the Protestant canon (cf.
  199. Westminster Confession 1.3). Other Septuagint pluses in canonical books
  200. (3 Kingdoms 2:35a–o, Proverbs 9:12a–c, ...) are textual variants and are not
  201. marked.
  202. - **LXX-only verses** (pluses such as the Prayer of Azariah, Psalm 151, and the
  203. Septuagint-only books) have no canonical MT position, so they never appear as
  204. the counterpart of a different MT verse. Request them with `numbering="lxx"`; a
  205. canonical lookup notes when such verses sit at the same Greek-numbered
  206. position. Septuagint-only books (Tobit, Sirach, ...) always use Greek numbering.
  207. New Testament references, unparseable references, and references with no
  208. matching verses each return a specific message. A database without the
  209. Septuagint table tells you to run `python scripts/upgrade_database.py`.
  210. #### `search_ancient_sources`
  211. Search licensed primary-source corpora for Jewish history. `corpus` is any
  212. registered corpus key or `all`; the registry (`src/study_bible_mcp/corpora/`)
  213. currently holds `josephus`: 2,304 Whiston sections from *Jewish Antiquities*,
  214. *The Jewish War*, *Life*, and *Against Apion*. Each section is paired with
  215. every Niese Greek section it spans and referenced as a Niese span plus
  216. Whiston's numbering, e.g. `Antiquities 15.317–322 (Whiston 15.9.3)`. `targum`
  217. holds Targum Onkelos on the five books of the Torah: 5,846 Aramaic verse
  218. passages with the CC BY-NC Metsudah English, an English of the Hebrew in which
  219. Onkelos's own renderings are marked `⟨…⟩` (see [Targums](#targums)), each
  220. linked to the verse it translates. `qumran`
  221. holds 44 Hebrew manuscript columns with numbered lines, no English translation
  222. included: the Damascus Document (`CD 1:1–21`, Genizah MS A columns 1–16
  223. and MS B columns 19–20), the Community Rule (`1QS`), the Rule of the
  224. Congregation (`1QSa`) and Pesher Habakkuk (`1QpHab`), all from the ETCBC/dss
  225. transcription; 32 curated links name the Habakkuk verses each 1QpHab lemma
  226. quotes. `philo` holds the 31 Greek treatises of Philo of Alexandria
  227. (Cohn–Wendland, via First1KGreek), one passage per Cohn–Wendland section with
  228. the same section of Yonge's English (7,901 passages; 58 sections of *Spec.* 1–2
  229. that Yonge's text lacks are Greek only). `pseudepigrapha` holds 1 Enoch in
  230. R. H. Charles's English, one passage per Charles verse, and 4 Ezra (2 Esdras
  231. 3–14) in the KJV with the Clementine Latin, one passage per verse (1,679
  232. passages); both works are non-canonical and are labelled as attributed to
  233. Enoch or Ezra. The
  234. `rabbinic` corpus holds the Mishnah from Sefaria (63 tractates, one passage per
  235. mishnah). Each result gives its citation and, on the line below, its
  236. canon-and-date tag (e.g. `*Not Scripture · Jewish pseudepigraphon (Parables,
  237. c. 50 BC–AD 117, debated) · tier A/B · Charles 1912*`), then up to 1,500
  238. characters of English around the first match and a shorter original-language
  239. excerpt (match-centred when the query is in the original's script; a passage
  240. without English shows its original instead), any editorial `⚠` notes, and its
  241. typed biblical links. A closing **Caveats** block prints each corpus's caveat
  242. and the date tiers present once, and a **Sources** block lists the edition,
  243. translation, license (non-commercial licences marked and linked), and pinned
  244. source once. Up to 4 passages are returned by default, within a
  245. 12,000-character budget (see [Ancient sources](#ancient-sources)).
  246. ```text
  247. search_ancient_sources(
  248. query="John Baptist",
  249. corpus="josephus",
  250. biblical_reference="Mark 6:20",
  251. period="second_temple",
  252. limit=4
  253. )
  254. ```
  255. Only the passage text is searched, so a word that appears only in a work
  256. title (`Jewish`, `War`, `Life`) does not match every passage of that work.
  257. English search is stemmed (`build` matches `building`); Greek, Hebrew, and
  258. Aramaic search ignores accents, breathings, vowel points, cantillation, and case
  259. (`βαπτισμω` matches `βαπτισμῷ`), and editorial signs printed inside a word
  260. (`יעבורו` matches the corrected `י{{א}}<<ע>>בורו`); Qumran text in `[ ]` is a
  261. modern reconstruction and is never matched. Passages containing every query word come
  262. first; when none do, passages matching any word are returned with an explicit
  263. note. Only when the exact search finds nothing is a Hebrew or Aramaic word
  264. retried with one or two attached prefix letters (ו ב ה ל מ כ ש) stripped from
  265. the indexed words, keeping at least three letters (`הון` then finds `ובהון`);
  266. those results are marked `(prefix match)`, because a root letter can look like
  267. a prefix (`קדש` finds `מקדש`). `biblical_reference` accepts a chapter, verse,
  268. or range (`Luke 21`, `Luke 21:5`, `Luke 21:5-6`, `Jude 6`) and filters to
  269. editorial links: curated links (33 for Josephus, 2 for the rabbinic corpus),
  270. each checked against the linked passage text, links from
  271. `corpora/editorial_notes.json`, and one "Translation of" link per targum
  272. verse, derived from its verse key (`biblical_reference="Deuteronomy 32:8"`
  273. with `corpus="targum"` finds Onkelos on that verse). Each link is typed —
  274. `Aligned`, `Echo`, `Shared tradition`, `Contrast`, or `Translation of` — and
  275. printed as e.g. `- Shared tradition: Mark 6:17–29 — Related account: death of
  276. John the Baptist`. Period tags,
  277. biblical links, and editorial chapter headings (Whiston's, for Josephus) are
  278. labelled editorial metadata; they are not presented as claims made by the
  279. ancient author. Empty results say whether the corpus is missing, the reference
  280. is unsupported, the reference has no curated link, or nothing matched.
  281. #### `lookup_ancient_source`
  282. Read an ancient-source passage by its citation. A citation is a work name or
  283. abbreviation plus a locator in that work's numbering; an author prefix is
  284. optional. For Josephus: `Antiquities`/`Ant.`/`A.J.`, `War`/`B.J.`/`J.W.`, and
  285. `Against Apion`/`C. Ap.` take Niese `book.section`; `Life`/`Vita` takes a
  286. section.
  287. For Targum Onkelos, `Targum Onkelos`/`Onkelos`/`Tg. Onq.` precedes a Torah
  288. book (`Genesis`/`Gen`, `Exodus`/`Exod`, `Leviticus`/`Lev`, `Numbers`/`Num`,
  289. `Deuteronomy`/`Deut`) and `chapter:verse`; the prefix is optional, so a bare
  290. `Genesis 1:1` also finds Onkelos. Onkelos is cited by English verse numbers,
  291. like the rest of the server; where Sefaria's Hebrew (MT) numbering differs,
  292. the heading and link show it: `Targum Onkelos Exodus 8:5 (MT 8:1)`, and the
  293. Peniel verse is `Onkelos Genesis 32:30 (MT 32:31)`. Sefaria joins the four
  294. short commandments into one verse, served as `Exodus 20:13–16` and
  295. `Deuteronomy 5:17–20`. For Qumran: `CD`/`Damascus Document`/`Zadokite Fragments`, `1QS`/
  296. `Community Rule`, `1QSa`/`1Q28a`/`Rule of the Congregation`, and
  297. `1QpHab`/`Pesher Habakkuk` take `column:line`, with Arabic or Roman column
  298. numbers (`CD 6:11`, `CD VI 11`, `1QpHab VII 1-5`); a line citation shows the
  299. cited lines ±2 from the column that contains them, and a column citation
  300. (`CD 6`) the whole column, with the line numbers in the text.
  301. For Philo, SBL short titles, Latin titles, and English titles
  302. (`Opif.`/`De Opificio Mundi`/`On the Creation of the World`, `Legat.`/`Leg.
  303. Gai.`, `Her.`/`Heres`, ...) take a Cohn–Wendland section; the multi-book works
  304. `Leg.` 1–3, `Somn.` 1–2, `Mos.` 1–2, and `Spec.` 1–4 take `book.section`; a
  305. book number the work lacks (`Leg. 31`, likewise `Ant. 21.1`) is rejected
  306. rather than read as a book.
  307. `1 Enoch`/`1 En.` and `4 Ezra`/`2 Esdras`/`4 Esdras` take `chapter:verse`.
  308. 4 Ezra 3–14 is 2 Esdras 3–14 with the same chapter numbers, so `2 Esdras 11:1`
  309. and `4 Ezra 11:1` are the same passage; 2 Esdras 1–2 and 15–16 (5 and 6 Ezra)
  310. are not included. 4 Ezra is cited in modern (Bensly) numbering: the KJV and
  311. Clementine Latin lack the "missing fragment" 7:36–105, so their 7:36–70 is
  312. 4 Ezra 7:106–140, shown as e.g. `4 Ezra 7:106 (KJV 2 Esdras 7:36)`. A 4 Ezra
  313. citation outside the served text says what is missing and why.
  314. For the Mishnah, a tractate takes `chapter:mishnah`, with an optional
  315. `Mishnah`/`m.` prefix (`Mishnah Shekalim 1:1`, `m. Shek. 1:1`). Tractate names
  316. follow Sefaria (`Menachot`, `Pesachim`) with SBL abbreviations and common
  317. spellings as aliases (`Menahot`, `Men.`, `Pesah.`, `B. Bat.`); apostrophes are
  318. ignored, so `Ta'anit 2:1` is `Taanit 2:1`.
  319. ```text
  320. lookup_ancient_source(citation="Ant. 15.320") # inside Antiquities 15.317–322
  321. lookup_ancient_source(citation="Josephus, War 6.316")
  322. lookup_ancient_source(citation="Antiquities 18.116-121", include_original=False)
  323. lookup_ancient_source(citation="Tg. Onq. Deut 32:8")
  324. lookup_ancient_source(citation="Onkelos Genesis 1:1-3")
  325. lookup_ancient_source(citation="CD 6:11") # inside CD 6:1–21 (CD-A)
  326. lookup_ancient_source(citation="1QpHab 7:4")
  327. lookup_ancient_source(citation="Philo, Legat. 299")
  328. lookup_ancient_source(citation="Leg. 1.31")
  329. lookup_ancient_source(citation="1 Enoch 89:73")
  330. lookup_ancient_source(citation="2 Esdras 11:1") # = 4 Ezra 11:1
  331. lookup_ancient_source(citation="m. Shek. 1:3")
  332. ```
  333. A locator inside a longer passage returns the passage containing it; a range
  334. returns the overlapping passages in citation order, 4 by default (`limit` up
  335. to 10), with a note when more exist. Each passage shows its citation,
  336. canon-and-date tag, up to 1,500 characters of English and 600 of the original
  337. (`full_text=true` lifts these caps), editorial `⚠` notes, and typed biblical
  338. links; caveats and sources are printed once at the end, and the response
  339. stops at about 12,000 characters, naming the citation to continue from. If
  340. registered works share a title, a collection prefix (such as `Mishnah`) or the
  341. locator grammar itself selects one.
  342. Unknown works get a short summary of the citable works (and a close match,
  343. e.g. `Did you mean Antiquities?`), ambiguous citations list the candidates,
  344. unreadable or missing locators name the expected grammar with an example from
  345. the same work, a locator outside the imported text names the imported range,
  346. the nearest passages, and any `gap` note covering it, and a database without
  347. the corpus (or with ancient-source tables from before the current schema) is
  348. told to run `python scripts/upgrade_database.py`.
  349. #### 2. `word_study`
  350. Deep dive into a Greek or Hebrew word's meaning, usage, and etymology. Greek entries include both the full Liddell-Scott-Jones (LSJ) definition for classical breadth and the Abbott-Smith definition for NT-specific insight (with LXX/Hebrew equivalents, synonym discussions, and NT occurrence counts). Hebrew entries include the full Brown-Driver-Briggs (BDB) definition.
  351. **When Claude uses it**: User asks about the meaning of a Greek/Hebrew word, wants to understand different translations of a term, or asks about theological concepts (love, faith, grace).
  352. **What it returns**: Original word in Greek/Hebrew script, transliteration, Strong's number, brief definition, full LSJ or BDB scholarly definition, Abbott-Smith NT-focused definition (Greek words), LXX/Hebrew cross-references, synonym discussions, NT occurrence count, etymology, usage count, semantic range, related words, example passages.
  353. **Example**:
  354. ```
  355. User: "What does 'agape' mean in Greek?"
  356. Claude calls: word_study(strongs="G26")
  357. Returns:
  358. - ἀγάπη (agapē, G26)
  359. - Brief Definition: "love, goodwill, benevolence"
  360. - Full LSJ Definition: [scholarly entry with classical and biblical usage]
  361. - Abbott-Smith Definition: [NT-focused entry with sense hierarchy]
  362. - LXX / Hebrew Equivalents: H0160 אַהֲבָה
  363. - Synonyms: SYN.: φιλία — love which chooses its object...
  364. - NT Usage: Occurs 116 times in the New Testament
  365. - Related words: ἀγαπάω (to love), ἀγαπητός (beloved)
  366. ```
  367. #### 3. `search_lexicon`
  368. Search across Greek and Hebrew lexicons by English meaning.
  369. **When Claude uses it**: User wants to find the Greek/Hebrew word for an English concept, asks "How do you say X in Greek?", or is exploring related words.
  370. **Example**:
  371. ```
  372. User: "What are the Greek words for 'love'?"
  373. Claude calls: search_lexicon(query="love", language="greek")
  374. Returns:
  375. - G26 ἀγάπη - divine, unconditional love
  376. - G5368 φιλέω - brotherly, affectionate love
  377. - G2309 θέλω - desire, wish
  378. ```
  379. #### 4. `get_cross_references`
  380. Find passages related to a verse or theological theme.
  381. **When Claude uses it**: User asks "What other passages talk about X?", wants to see Scripture interpreting Scripture, or is studying a theological theme.
  382. **Built-in themes**: `salvation_by_grace`, `deity_of_christ`, `atonement`, `resurrection`, `holy_spirit`, `justification`.
  383. **Example**:
  384. ```
  385. User: "What passages support salvation by grace alone?"
  386. Claude calls: get_cross_references(theme="salvation_by_grace")
  387. Returns:
  388. - Genesis 15:6 - Abraham believed, credited as righteousness
  389. - Romans 3:21-26 - Righteousness through faith in Christ
  390. - Ephesians 2:8-9 - Saved by grace through faith
  391. - Titus 3:5-7 - Not by works of righteousness
  392. ```
  393. #### 5. `lookup_name`
  394. Get information about biblical people, places, and things, enriched with ACAI entity annotations (variant names, roles, reference counts, speech attributions).
  395. **When Claude uses it**: User asks "Who was X?", wants to know about a place's significance, or asks about relationships between biblical figures.
  396. **What it returns**: Original Hebrew/Greek form, type (person, place, thing), description, key references, relationships (father, mother, children), ACAI annotations (variant names, roles, verse reference count, attributed speeches).
  397. **Example**:
  398. ```
  399. User: "Who was Abraham?"
  400. Claude calls: lookup_name(name="Abraham")
  401. Returns:
  402. - Type: Person
  403. - Original: אַבְרָהָם
  404. - Description, key references, family relationships
  405. - ACAI: Also known as "Abram", referenced in 275 verses, 52 attributed speeches
  406. ```
  407. #### 6. `parse_morphology`
  408. Explain Greek or Hebrew grammatical parsing codes.
  409. **When Claude uses it**: User asks what a morphology code means or wants to understand verb tense, mood, voice.
  410. **Example**:
  411. ```
  412. User: "What does V-AAI-3S mean?"
  413. Claude calls: parse_morphology(code="V-AAI-3S", language="greek")
  414. Returns:
  415. - Part of Speech: Verb
  416. - Tense: Aorist, Voice: Active, Mood: Indicative
  417. - Person: 3rd, Number: Singular
  418. ```
  419. #### 7. `search_by_strongs`
  420. Find all verses containing a specific Strong's number.
  421. **When Claude uses it**: User wants to see how a word is used throughout Scripture or is doing a comprehensive word study.
  422. **Example**:
  423. ```
  424. User: "Show me all the places where 'hesed' (H2617) appears"
  425. Claude calls: search_by_strongs(strongs="H2617", limit=20)
  426. Returns:
  427. - H2617 חֶסֶד (hesed) - "lovingkindness, steadfast love"
  428. - Genesis 24:12, Exodus 34:6, Psalm 23:6, Psalm 136...
  429. ```
  430. ### Scholarly Commentary
  431. #### 8. `get_study_notes`
  432. Get scholarly study notes and translation notes for a Bible verse or chapter.
  433. **When Claude uses it**: User wants commentary on a specific verse, help explaining a difficult passage, or translation and cultural background notes.
  434. **What it returns**: Combined commentary from three sources: Aquifer Open Study Notes (66 books of concise verse-level scholarly commentary), unfoldingWord Translation Notes (translator-focused linguistic insights), and SIL Translator Notes (additional translation and cultural context).
  435. **Example**:
  436. ```
  437. User: "What do the study notes say about John 3:16?"
  438. Claude calls: get_study_notes(reference="John 3:16")
  439. Returns:
  440. - Aquifer Open Study Notes: [verse commentary]
  441. - Translation Notes (UW): [linguistic insights]
  442. - Translation Notes (SIL): [cultural context]
  443. ```
  444. #### 9. `get_bible_dictionary`
  445. Look up a topic in the Tyndale Bible Dictionary.
  446. **When Claude uses it**: User needs background information on a biblical topic, historical or cultural context, or a detailed article about a person, place, or concept.
  447. **What it returns**: The dictionary article from a collection of 500+ topical articles covering biblical people, places, theological concepts, cultural practices, historical background, and archaeological findings. A long article comes about 4,000 characters at a time, ending with the `offset` to continue from and the headings of the sections still to come (`section="The Sinai Covenant"` reads one section). When no article is titled exactly as the topic, it returns at most four: titles containing the topic first (`Gilboa` gives Mount Gilboa), then articles that mention it.
  448. **Example**:
  449. ```
  450. User: "Tell me about the Pharisees"
  451. Claude calls: get_bible_dictionary(topic="Pharisees")
  452. Returns: Full Tyndale Bible Dictionary article with historical background,
  453. beliefs, practices, and NT context.
  454. ```
  455. #### 10. `get_key_terms`
  456. Look up a key theological term in the FIA Key Terms database.
  457. **When Claude uses it**: User wants a precise definition of a theological term, or needs to understand how a concept is used across Scripture.
  458. **What it returns**: Definition from a collection of 200+ carefully defined theological and biblical terms with biblical usage, cross-references, and translation guidance.
  459. **Example**:
  460. ```
  461. User: "Define the term atonement"
  462. Claude calls: get_key_terms(term="atonement")
  463. Returns: FIA Key Terms definition with biblical usage, cross-references,
  464. and translation guidance.
  465. ```
  466. ### Graph Knowledge (Theographic Bible Metadata)
  467. #### 11. `explore_genealogy`
  468. Trace family relationships (ancestors or descendants, 1 to 40 generations) for a biblical person using the parent links of 2,000 persons.
  469. **What it returns**: Each ancestor or descendant once, generation by generation, with whose parent or child they are (and curated notes such as Joseph as Jesus' legal father), immediate family (spouse, siblings), and a Mermaid diagram when the tree has at most 40 people. Dictionary articles are left to `get_bible_dictionary`.
  470. **Example**:
  471. ```
  472. User: "Show me the family tree of David"
  473. Claude calls: explore_genealogy(person="David", direction="both", generations=5)
  474. Returns: Ancestor chain (Jesse → Obed → Boaz...), descendants,
  475. spouse(s), siblings, Mermaid flowchart diagram.
  476. ```
  477. #### 12. `explore_person_events`
  478. Find all events a biblical person participated in, in chronological order.
  479. **What it returns**: Each event once, in chronological order, with its approximate date (Theographic chronology), places, and passage. Names resolve as Scripture uses them ('Peter', 'Jacob' the patriarch), and the tool says which namesake it chose.
  480. #### 13. `explore_place`
  481. Explore the biblical history of a geographic location.
  482. **What it returns**: Events at the location in chronological order with their passages, people born or who died there, coordinates, Mermaid network diagram.
  483. #### 14. `find_connection`
  484. Find the family relationship path between two biblical people.
  485. **What it returns**: The closest relationship path through parent, child, sibling, and partner relationships, preferring lines of descent, summarised and listed compactly, with a Mermaid flowchart for paths of up to 12 steps.
  486. **Example**:
  487. ```
  488. User: "How are Ruth and Jesus related?"
  489. Claude calls: find_connection(person1="Ruth", person2="Jesus")
  490. Returns: Ruth → child → Obed → child → Jesse → child → David → ... → Jesus
  491. ```
  492. #### 15. `people_in_passage`
  493. Find all people, places, and events mentioned in a Bible passage.
  494. **What it returns**: All entities mentioned in a chapter or verse according to Theographic Bible Metadata.
  495. ### Cultural Context
  496. #### 18. `get_ane_context`
  497. Retrieve Ancient Near East cultural and historical context that illuminates biblical passages. Covers 12 dimensions of ANE life across 9 time periods.
  498. **When Claude uses it**: User asks about cultural background, customs, practices, or worldview behind a passage; when understanding the original context would prevent modern misreadings.
  499. **What it returns**: Structured entries with title, summary, detailed explanation, ANE parallels from extra-biblical sources, interpretive significance, key references, and scholarly sources.
  500. **Dimensions**: Cosmology & Worldview, Religious Practices, Social Structure, Legal & Covenant, Political & Imperial, Economic Life, Literary Conventions, Warfare & Military, Daily Life & Material Culture, Death & Afterlife, Gender & Family, Education & Literacy.
  501. **Periods**: Patriarchal, Exodus/Conquest, Judges/Early Monarchy, United Monarchy, Divided Monarchy, Assyrian/Babylonian, Persian, Hellenistic, Roman.
  502. **Example**:
  503. ```
  504. User: "What's the cultural background behind Genesis 15 - the covenant ceremony?"
  505. Claude calls: get_ane_context(reference="Genesis 15:1", dimension="legal_covenant")
  506. Returns:
  507. - Suzerainty Treaty Forms: ANE covenant structure (preamble, stipulations,
  508. witnesses, curses/blessings) parallels Deuteronomy and Genesis 15
  509. - Self-Maledictory Oath: Walking between animal halves = "may I become
  510. like these animals if I break this covenant"
  511. - ANE Parallels: Hittite suzerainty treaties, Mari covenant rituals
  512. - Interpretive Significance: God alone passes through the pieces,
  513. taking the covenant curse entirely upon himself
  514. ```
  515. ### Hybrid Search
  516. #### 16. `graph_enriched_search`
  517. Combine passage lookup with graph context for the most comprehensive single-query view of a verse.
  518. **What it returns**: Verse text (English + original), all people/places/events mentioned, family relationships for each person mentioned.
  519. #### 17. `find_similar_passages`
  520. Discover semantically similar passages across the Bible using vector embeddings.
  521. **When Claude uses it**: User wants to find thematic connections not captured by explicit cross-references, or asks "What passages are similar to X?"
  522. **What it returns**: Similar passages ranked by semantic similarity (%), genre warnings, hermeneutical cautions.
  523. **Important**: Semantic similarity indicates shared vocabulary and concepts, but does NOT establish theological connection. The tool includes warnings to verify genre compatibility, authorial intent, and historical context.
  524. **Example**:
  525. ```
  526. User: "Find passages similar to Daniel 7:7"
  527. Claude calls: find_similar_passages(reference="Daniel 7:7", limit=5)
  528. Returns:
  529. - Daniel 7:15-28 (70.0% similar) - interpretation of the vision
  530. - Revelation 9:17-21 (61.1% similar) - locusts with lion's teeth
  531. - Daniel 2:29-45 (60.8% similar) - Nebuchadnezzar's statue
  532. ```
  533. ### Theological Scholarship & Structure
  534. #### `get_theology_context`
  535. Retrieve attributed theological scholarship by biblical reference, theme, or author.
  536. #### `get_torah_weave`
  537. Find structurally paired Torah passages under Moshe Kline's Woven Torah hypothesis.
  538. #### `get_textual_variant`
  539. Inspect catalogued MT/LXX/DSS divergences without collapsing sources and
  540. conclusions. Each reading lists only the manuscripts that witness it. New
  541. Testament quotations appear under **NT citation evidence**, and material that
  542. bears on a text form without witnessing the verse (such as a Qumran scroll
  543. attesting a short edition elsewhere in Jeremiah) appears under **Indirect
  544. evidence**. Corpora with no surviving copy are listed in a case-level **Not
  545. preserved in** note. Every witness keeps the dataset's raw support label.
  546. **Critical judgments** contain only conclusions that carry a source citation.
  547. Uncited dataset summaries appear separately as an **Unsourced dataset summary
  548. (not verified against published text-critical scholarship)**. Theological
  549. interpretations, named-author claims, and NT quotation alignment also stay in
  550. their own sections, and sections with nothing catalogued are omitted. The
  551. dataset's Heiser Literal Translation (HLT) renderings and rationales stay in the
  552. database but are not printed: the HLT is the owner's own unpublished
  553. translation. Verses where the witnesses agree with the MT but the
  554. reading or rendering is contested (for example the divine-council language of
  555. Psalm 82:6) appear as **Translation and interpretation notes**, never as
  556. variants. A verse can have both: at Job 38:7, Daniel 4:17 and 7:13, and Psalm
  557. 29:1 a variant case records where the Greek differs from the MT, and the notes
  558. follow it; Mark 14:62, Matthew 24:30 and 26:64, and Revelation 1:7 reach the
  559. Daniel 7:13 case through NT quotation alignment. `lookup_verse` mentions when a verse has a catalogued variant case or
  560. interpretation notes. On a database that still has the legacy
  561. variant schema, the tool asks you to run `python scripts/upgrade_database.py`.
  562. ### Further Research
  563. #### `list_research_sources`
  564. List curated, freely accessible research repositories to consult before a general web search: primary-text libraries (Sefaria, CCEL, Perseus, the Internet Archive), open-access journals (Tyndale Bulletin, Themelios, the Journal of Hebrew Scriptures, HTS), Dead Sea Scrolls and Septuagint resources, and Heiser's own sites. Each entry states its coverage, perspective (Jewish, Catholic, Reformed, evangelical, academic/critical, multi-tradition, single-author) and access or licence terms. Filter by `topic` (coverage tag or name, matched loosely) and `perspective`; pass `query` to get a ready-to-open search link for every source that supports one (STEP Bible's link opens the passage when the query is a Bible reference). With no filter the list starts with a mix: Tyndale Bulletin (evangelical), STEP Bible (reference), Sefaria (Jewish) and Bible Odyssey (academic). The list is a set of places to look, not endorsements.
  565. The catalogue lives in [`src/study_bible_mcp/research_sources.json`](src/study_bible_mcp/research_sources.json). It is a directory of repositories, not a per-passage or per-scholar index.
  566. **Checking links.** `python scripts/check_links.py` fetches, over the network, every catalogue URL, every search template filled with a sample query, and (when `db/study_bible.db` or `--db` is present) every distinct `theology_content.url` in the database. It makes about 100 requests to third-party sites, so run it occasionally rather than in CI. Checks run with bounded concurrency and a 20-second timeout; a link that times out is retried once with a 60-second limit, because some hosts are slow rather than dead. Any link answering with status 400 or above, or failing at the network level, is reported as `BROKEN` with where it came from; one that still times out after the retry is reported as `TIMEOUT`. Either makes the run exit non-zero. Hosts known to be slow but working are listed in `LINK_CHECK_SLOW_HOSTS` in the script (currently `drmsh.com`, which has taken 31-57 seconds to answer): their retry gets a 180-second limit, and a timeout that still persists is reported as `SLOW`, a warning that does not fail the run. A real error status from those hosts still does. Some sites refuse `HEAD` requests, so the checker falls back to `GET`. Some answer every automated client with a bot challenge; only for those, an entry may set `"link_check": "skip"` with a `"link_check_reason"`, and the checker lists it as skipped rather than checking it. Verify skipped entries by hand when updating `last_verified`.
  567. ---
  568. ## How Users Interact
  569. ### Natural Language Queries
  570. Users don't need to know the tool names. They just ask questions:
  571. | User Question | Claude Uses |
  572. |--------------|-------------|
  573. | "What does John 3:16 say in Greek?" | `lookup_verse` |
  574. | "What's the Greek word for love?" | `search_lexicon` |
  575. | "Study the word 'agape'" | `word_study` |
  576. | "Who was Abraham?" | `lookup_name` |
  577. | "What other passages talk about grace?" | `get_cross_references` |
  578. | "Parse V-AAI-3S" | `parse_morphology` |
  579. | "Where else does G26 appear?" | `search_by_strongs` |
  580. | "What do the study notes say about Romans 8:28?" | `get_study_notes` |
  581. | "Look up 'covenant' in the Bible dictionary" | `get_bible_dictionary` |
  582. | "Define the key term 'atonement'" | `get_key_terms` |
  583. | "Show me David's family tree" | `explore_genealogy` |
  584. | "What events happened in Moses' life?" | `explore_person_events` |
  585. | "What's the history of Bethlehem?" | `explore_place` |
  586. | "How are Ruth and Jesus related?" | `find_connection` |
  587. | "Who are the people in Romans 8?" | `people_in_passage` |
  588. | "Give me everything about Genesis 22:1" | `graph_enriched_search` |
  589. | "Find passages similar to Daniel 7" | `find_similar_passages` |
  590. | "What's the cultural context of Genesis 15?" | `get_ane_context` |
  591. ### Example Conversation
  592. **User**: "I'm studying Romans 5:8. What does Paul mean when he says God 'demonstrates' his love?"
  593. **Claude's internal process**:
  594. 1. Look up the verse: `lookup_verse(reference="Romans 5:8")`
  595. 2. Study the key word: `word_study(word="demonstrates")` → finds G4921 συνίστημι
  596. 3. Get study notes: `get_study_notes(reference="Romans 5:8")`
  597. 4. Check cross-references for context
  598. 5. Apply genre guidance (Epistles)
  599. **Claude's response**:
  600. > In Romans 5:8, Paul uses the Greek word **συνίστημι** (synistēmi, G4921), which means "to stand together, to commend, to demonstrate." This is a present tense verb, indicating ongoing action.
  601. >
  602. > The genre context is important here: Romans is an epistle, and Paul is building an argument. In the immediate context (Romans 5:1-11), he's explaining how we have peace with God through justification by faith. Verse 8 is his proof: God didn't wait for us to become worthy, but demonstrated his love "while we were still sinners."
  603. >
  604. > The word "demonstrates" carries the sense of proving beyond doubt - not just telling us about his love, but showing it through action (Christ's death).
  605. >
  606. > Related passages on God's love demonstrated through Christ: John 3:16, 1 John 4:9-10.
  607. ---
  608. ## Example Questions
  609. Try asking Claude:
  610. ```
  611. What does John 3:16 say in Greek? Break down the key words.
  612. ```
  613. ```
  614. Study the word 'agape' - how is it different from other Greek words for love?
  615. ```
  616. ```
  617. What's the context of Romans 8:28? Who is Paul writing to and why?
  618. ```
  619. ```
  620. Show me cross-references for Ephesians 2:8-9 on salvation by grace.
  621. ```
  622. ```
  623. Who was Melchizedek and why is he significant?
  624. ```
  625. ```
  626. Parse the verb morphology in Philippians 2:12 - "work out your salvation"
  627. ```
  628. ```
  629. What does the Hebrew word 'hesed' mean? Where is it used?
  630. ```
  631. ```
  632. Help me understand Revelation 13 - what are these beasts?
  633. ```
  634. ```
  635. What do the study notes say about John 1:1?
  636. ```
  637. ```
  638. Look up 'baptism' in the Bible dictionary.
  639. ```
  640. ```
  641. Show me David's family tree going back 5 generations.
  642. ```
  643. ```
  644. How are Abraham and Jesus connected genealogically?
  645. ```
  646. ```
  647. What events happened in the life of Moses?
  648. ```
  649. ```
  650. Find passages similar to John 3:16 - what other verses talk about God's love like this?
  651. ```
  652. ```
  653. What Old Testament passages connect to Daniel's vision of the Son of Man?
  654. ```
  655. ```
  656. What's the Ancient Near East background for the creation account in Genesis 1?
  657. ```
  658. ```
  659. Explain the cultural context of covenant-making in Genesis 15.
  660. ```
  661. ---
  662. ## Hermeneutical Framework
  663. This isn't just a reference tool. It's designed to guide users toward sound biblical interpretation.
  664. ### The Problem It Solves
  665. Common interpretation errors include:
  666. - **Proof-texting**: Using isolated verses to support predetermined conclusions
  667. - **Allegorizing**: Finding hidden meanings not intended by the author
  668. - **Ignoring genre**: Reading poetry as prose or prophecy as history
  669. - **Ignoring context**: Ripping verses from their historical and literary setting
  670. - **Moralizing**: Reducing narratives to "be good like David"
  671. ### The Fee & Stuart Method
  672. The interpretive framework is based on **"How to Read the Bible for All Its Worth"** by Gordon Fee and Douglas Stuart - the standard textbook for biblical hermeneutics used in seminaries worldwide.
  673. **About the authors:**
  674. - **Gordon Fee** (1934-2022): New Testament scholar, professor at Regent College, author of major commentaries on 1 Corinthians, Philippians, and Pauline theology. One of the translators of the NIV and TNIV.
  675. - **Douglas Stuart**: Old Testament scholar, professor at Gordon-Conwell Theological Seminary, author of commentaries on Hosea-Jonah, Exodus, and Old Testament hermeneutics.
  676. Their book (first published 1981, now in its 4th edition) has sold over a million copies and is used as the introductory hermeneutics text at most evangelical seminaries. It teaches readers to interpret Scripture according to its literary genre, historical context, and authorial intent - avoiding both wooden literalism and uncontrolled allegorizing.
  677. The server embeds genre-specific interpretation principles from this methodology:
  678. #### Core Principles
  679. 1. **Exegesis Before Application**
  680. - First discover what the text meant to its original audience
  681. - Then determine what it means for us today
  682. - Never jump directly to application
  683. 2. **Context is King**
  684. - Historical context: time, culture, author, audience, occasion
  685. - Literary context: genre, surrounding passages, book structure
  686. - A text without context is a pretext for a proof text
  687. 3. **Genre Determines Method**
  688. Different biblical literature requires different approaches
  689. ### Genre-Specific Guidelines
  690. #### Epistles (Letters)
  691. **Key principle**: Think contextually - what problem was being addressed?
  692. - Read the entire letter to understand the argument flow
  693. - Ask: What problem prompted this letter?
  694. - Pay attention to logical connectors (therefore, because, so that)
  695. - Distinguish between central argument and supporting points
  696. - Not every statement is universally prescriptive
  697. **Common errors**:
  698. - Taking verses out of their argumentative context
  699. - Ignoring the specific historical situation being addressed
  700. - Treating every instruction as a timeless command
  701. #### Old Testament Narratives
  702. **Key principle**: Three levels (meta, national, individual); descriptive not prescriptive
  703. - Narratives describe what happened, not necessarily what should happen
  704. - Three levels: God's universal plan, Israel's story, individual accounts
  705. - Characters are not always examples to follow - observe their flaws
  706. - The narrator rarely makes direct theological statements
  707. - God is the ultimate hero of every narrative
  708. **Common errors**:
  709. - Treating every character's action as a model to follow
  710. - Allegorizing details that are simply historical facts
  711. - Moralizing: "Be brave like David" without seeing God's work
  712. #### Gospels
  713. **Key principle**: Two-level documents (Jesus' original context + evangelist's purpose)
  714. - Consider both Jesus' original meaning and the Gospel writer's purpose
  715. - Each Gospel has a specific audience and theological emphasis
  716. - Account for the already/not-yet tension of the Kingdom
  717. - Compare parallel accounts to see each writer's emphasis
  718. **Common errors**:
  719. - Harmonizing too quickly without hearing each Gospel's voice
  720. - Ignoring Jesus' audience (Pharisees, disciples, crowds)
  721. - Applying teachings directly without considering the cross
  722. #### Parables
  723. **Key principle**: Find the main point; don't allegorize every detail
  724. - Identify the one or two main points - parables are not allegories
  725. - Consider the audience: Who is Jesus speaking to and why?
  726. - Look for cultural background that illuminates meaning
  727. - The unexpected twist often carries the main message
  728. **Common errors**:
  729. - Allegorizing every detail (the donkey represents X...)
  730. - Missing the shock value for the original audience
  731. - Creating theological systems from parabolic details
  732. #### Prophets
  733. **Key principle**: Covenant enforcement; check if "future" is now past
  734. - Prophets were covenant enforcement officers - calling Israel back
  735. - Most "predictions" were about events now in our past
  736. - The prophetic lawsuit pattern: accusation, judgment, hope
  737. - Distinguish near fulfillment from ultimate/eschatological fulfillment
  738. - Poetry and metaphor are the normal mode of prophetic speech
  739. **Common errors**:
  740. - Reading all prophecy as about the end times
  741. - Literalizing poetic and metaphorical language
  742. - Creating detailed end-times timelines from prophetic poetry
  743. #### Psalms
  744. **Key principle**: Poetry/prayer; understand the types (lament, thanksgiving, praise)
  745. - Psalms are inspired responses to God - poetry, not doctrine
  746. - Identify the type: Lament, Thanksgiving, Praise, Royal, Wisdom
  747. - Poetry uses metaphor, hyperbole, and parallelism
  748. - The emotions are real and God-given - even the difficult ones
  749. - Many psalms find their ultimate fulfillment in Christ
  750. **Common errors**:
  751. - Treating poetic expressions as doctrinal statements
  752. - Ignoring the emotional dimension
  753. - Literalizing metaphorical language
  754. #### Wisdom Literature
  755. **Key principle**: General truths, not guarantees; compare with full canon
  756. - Proverbs are general truths, not unconditional promises
  757. - Wisdom literature wrestles with life's complexity
  758. - Job and Ecclesiastes challenge simplistic interpretations
  759. - The fear of the Lord is the foundation of all wisdom
  760. - Compare individual proverbs with the full biblical witness
  761. **Common errors**:
  762. - Treating Proverbs as unconditional promises
  763. - Ignoring the dialogue format in Job (not all speeches are true)
  764. - Missing the "under the sun" perspective in Ecclesiastes
  765. #### Apocalyptic (Revelation)
  766. **Key principle**: Apocalyptic imagery; already/not yet eschatology
  767. - Apocalyptic is a literary genre with its own conventions
  768. - Symbols are stock imagery (beasts, numbers) with recognized meanings
  769. - The primary message is: God wins, evil is judged, Christ reigns
  770. - Read in light of OT prophets and the already/not yet tension
  771. - Multiple valid interpretive approaches exist
  772. **Common errors**:
  773. - Literalizing symbolic imagery (666 as a barcode)
  774. - Creating detailed chronological timelines
  775. - Missing the pastoral purpose: encouragement for suffering believers
  776. ### The Reasoning Pattern
  777. The server's hermeneutics module guides Claude through this sequence:
  778. 1. **IDENTIFY**: What biblical text(s) are relevant?
  779. 2. **GENRE**: What type of literature is this?
  780. 3. **CONTEXT**: Historical, literary, canonical
  781. 4. **CONTENT**: What does the text say? (Greek/Hebrew when helpful)
  782. 5. **CROSS-REFERENCES**: Scripture interprets Scripture
  783. 6. **APPLICATION**: Timeless principle behind temporal commands
  784. 7. **HUMILITY**: Acknowledge uncertainty where it exists
  785. ---
  786. ## Self-Hosting
  787. Want to run your own instance? See [docs/SELF_HOST.md](docs/SELF_HOST.md).
  788. Options:
  789. - Local Python development
  790. - Docker deployment
  791. - Your own Fly.io instance
  792. ---
  793. ## Project Structure
  794. ```
  795. studybible-mcp/
  796. ├── src/study_bible_mcp/
  797. │ ├── server.py # MCP server (stdio, SSE, and Streamable HTTP)
  798. │ ├── database.py # SQLite queries (async)
  799. │ ├── tools.py # MCP tool definitions and output formatters
  800. │ ├── research_sources.json # Curated open research repositories (list_research_sources)
  801. │ ├── hermeneutics.py # Genre detection & interpretation
  802. │ ├── corpora/ # Ancient-source corpus registry
  803. │ │ ├── __init__.py # CORPORA registry (one line per corpus)
  804. │ │ ├── base.py # Corpus, Work, Collection, BiblicalLink types
  805. │ │ ├── locators.py # Citation locator grammars and sort keys
  806. │ │ ├── citations.py # Citation-to-work resolution
  807. │ │ ├── download.py # Checksum-verified download helpers
  808. │ │ ├── josephus.py # Josephus TEI parser, works, and links
  809. │ │ ├── targum.py # Targum Onkelos Sefaria files, verse keys
  810. │ │ └── rabbinic.py # Mishnah (Sefaria)
  811. │ └── parsers/
  812. │ ├── lexicon.py # TFLSJ, BDB, Abbott-Smith, TBESG, TBESH parsers
  813. │ ├── aquifer.py # BibleAquifer JSON parser
  814. │ ├── acai.py # ACAI entity annotation parser
  815. │ ├── ane_context.py # ANE cultural context parser
  816. │ ├── biblical_versions.py # MT/LXX text, morphology, and versification
  817. │ ├── bsb.py # Berean Standard Bible (bsb.txt) parser and importer
  818. │ ├── ancient_sources.py # Generic corpus importer (passages, FTS, links)
  819. │ ├── tagged_text.py # TAGNT/TAHOT morphology parsers
  820. │ └── proper_names.py # TIPNR name parser
  821. ├── scripts/
  822. │ ├── download_stepbible.py # Download base source data (--aquifer flag)
  823. │ ├── download_biblical_versions.py # Download pinned LXX/Brenton sources
  824. │ ├── download_bsb.py # Download the pinned Berean Standard Bible text
  825. │ ├── download_ancient_sources.py # Download every registered ancient corpus
  826. │ ├── build_database.py # Build SQLite database
  827. │ ├── generate_embeddings.py # Generate vector embeddings
  828. │ ├── import_theographic.py # Import Theographic graph data
  829. │ ├── upgrade_database.py # In-place schema/source upgrade of an existing DB
  830. │ ├── smoke_server.py # Full-database smoke suite
  831. │ └── check_links.py # Checks research-source and theology URLs (network)
  832. ├── tests/ # Deterministic unit and tool-selection tests
  833. ├── prompts/
  834. │ └── system_prompt.md # Full hermeneutical framework for agents
  835. ├── docs/
  836. │ ├── SETUP.md # Quick setup guide
  837. │ └── SELF_HOST.md # Self-hosting instructions
  838. ├── ARCHITECTURE.md # Mermaid flowchart of the tool-selection paths
  839. ├── Dockerfile # Runtime image; database mounted separately
  840. ├── fly.toml # Fly.io deployment config
  841. └── pyproject.toml
  842. ```
  843. ---
  844. ## Data Sources
  845. ### STEPBible - Tyndale House, Cambridge
  846. Biblical text and brief lexicon data come from the [STEPBible project](https://www.stepbible.org/) ([GitHub](https://github.com/STEPBible/STEPBible-Data)), developed by scholars at **Tyndale House, Cambridge** - one of the world's leading centres for biblical research. Licensed CC BY 4.0.
  847. | File | Description | Content |
  848. |------|-------------|---------|
  849. | **TFLSJ** | Full Liddell-Scott-Jones Greek Lexicon | 10,846 Greek words with full scholarly definitions |
  850. | **Abbott-Smith** | Manual Greek Lexicon of the NT (TEI XML) | 5,896 NT-focused entries with LXX cross-refs and synonym discussions |
  851. | **TBESG** | Tyndale Brief Lexicon - Greek (fallback) | 5,600+ Greek words with brief definitions |
  852. | **TBESH** | Tyndale Brief Lexicon - Hebrew (fallback) | 8,600+ Hebrew words with brief definitions |
  853. | **TAGNT** | Translators Amalgamated Greek NT (2 parts) | Every word of the Greek NT with morphology, Strong's numbers, glosses |
  854. | **TAHOT** | Translators Amalgamated Hebrew OT (4 parts) | Every word of the Hebrew OT with morphology, Strong's numbers, glosses |
  855. | **TIPNR** | Translators Proper Names | 4,299 biblical people, places, and things with references |
  856. | **TEGMC/TEHMC** | Morphology Codes | Grammatical parsing code definitions |
  857. ### Berean Standard Bible
  858. The English verse text shown by `lookup_verse`, `search_by_strongs`,
  859. `word_study`, `find_similar_passages` and `graph_enriched_search` is the
  860. [Berean Standard Bible](https://bereanbible.com/), which its publisher has
  861. dedicated to the public domain. `scripts/download_bsb.py` fetches `bsb.txt`
  862. from bereanbible.com, which is unversioned, so the file is pinned by SHA-256
  863. (`BSB_SHA256` in `src/study_bible_mcp/parsers/bsb.py`, the edition downloaded
  864. on 2026-10-14); the download and import fail on any other file. The import also
  865. requires the file's own public-domain statement, and moves the Psalm headings
  866. the file prints at the start of verse 1 into verse 0 rows, so a Psalm's
  867. superscription shows its BSB heading and verse 1 is the verse alone. Verses are matched by English
  868. numbering, so split-numbered STEPBible rows (`Gen.32.1(32.2)`) get their BSB
  869. verse; where the BSB has no such verse the tools show the STEPBible gloss
  870. marked `[gloss]`, and without the table they show the gloss as before.
  871. ### Septuagint and MT versification
  872. The LXX comparison corpus uses the complete 59-book
  873. [OpenScriptorium `lxx-morph`](https://github.com/OpenScriptorium/lxx-morph)
  874. Rahlfs morphology dataset, pinned to commit
  875. `c91f6b1e8fb3ba37df701e6ae31f675ace71a2b2`. Its explicit
  876. `verse_pairs.jsonl` mapping resolves Psalm numbering, Jeremiah's chapter order,
  877. 2 Esdras, and smaller MT/LXX shifts. That mapping is derived in part from
  878. [TVTMS](https://github.com/STEPBible/STEPBible-Data) (Tyndale Versification
  879. Traditions Mapping System), CC BY 4.0, created by STEPBible.org / Tyndale House
  880. Cambridge. Downloads are checked against the pinned
  881. Git blob hashes. Morphology is CC BY 4.0; the underlying Rahlfs (1935) Greek
  882. text is public domain. Only the LXX rows are stored (about 35 MB including
  883. indexes, with word morphology zlib-compressed); MT rows are read from the
  884. existing TAHOT `verses` table at query time.
  885. English LXX translations come from the public-domain
  886. [Brenton Septuagint at eBible.org](https://ebible.org/details.php?id=eng-Brenton),
  887. and Brenton's own public-domain Greek text from
  888. [eBible's grcbrent](https://ebible.org/details.php?id=grcbrent)
  889. (`data/lxx/brenton-greek`). eBible regenerates its unversioned zips, so the
  890. download script verifies the SHA-256 of every extracted USFM book rather than of
  891. the archive, and never deletes or overwrites local files that fail verification.
  892. Brenton's Greek is stored only for the verses where it differs from Rahlfs
  893. (about 5 MB). `build_database.py` stops with an error if `data/lxx` is present
  894. but incomplete (any of the 59 morphology books, the mapping, a required Brenton
  895. English or Greek book, or a manifest-listed file is missing or truncated).
  896. ### Ancient sources
  897. The ancient sources are texts written by about AD 200 that witness the Second
  898. Temple world: Josephus, Targum Onkelos, four Qumran texts (CD, 1QS, 1QSa,
  899. 1QpHab), Philo, 1 Enoch, 4 Ezra and the Mishnah. Targum Onkelos is the one
  900. stated exception: its final form is c. 3rd–5th c. AD, and it is kept for its
  901. earlier tradition as the standard Torah targum; its tag gives the final-form
  902. date and its caveat states the exception. Sources later than c. AD 200
  903. (Targum Pseudo-Jonathan with Etheridge's English, the Tosefta, the Babylonian
  904. Talmud and Leviticus Rabbah) were removed: they are too far from the New
  905. Testament to witness its world without an earlier source.
  906. Each corpus is a module in `src/study_bible_mcp/corpora/` registered in
  907. `CORPORA`; its pinned files live in `data/ancient_sources/<corpus>/` and
  908. `source_manifest.json` records every verified file. `build_database.py`
  909. imports every corpus whose directory exists and fails if a present directory is
  910. incomplete; `upgrade_database.py` fails unless every registered corpus is
  911. downloaded and complete. All corpora share `ancient_source_passages`,
  912. whose `sort_start`/`sort_end` keys (in each work's citation grammar) back
  913. `lookup_ancient_source`, and whose `original_license`, `translation_license`,
  914. and combined `license` record provenance per passage. Each import replaces only
  915. its own corpus inside a savepoint after validating every passage and link, and
  916. merges the FTS index so repeated upgrades do not grow it. Indexed originals are
  917. folded for search: Greek accents and breathings and Hebrew/Aramaic vowel points
  918. and cantillation are removed and case is folded, in the index and the query.
  919. Editorial signs inside words (`[ ] ⟨ ⟩ < > { } ( ) ^ ¦`) and invisible format
  920. characters are deleted rather than treated as word breaks, in the index and the
  921. query; a corpus can also declare `search_index_removals`, patterns for printed
  922. text that is not part of the reading (Qumran's scribal erasures and `vacat`),
  923. which are deleted from the index, and `search_index_gaps`, printed text that
  924. is not evidence (Qumran's `[ ]` reconstruction), which becomes a word break, so
  925. it is never matched and the surviving letters either side are not joined into
  926. a false word. Every Hebrew-script word is also indexed,
  927. in a separate column searched only as a fallback, without one or two leading
  928. prefix letters, keeping at least three letters. The displayed text keeps
  929. every sign.
  930. Every passage is labelled so that the agent never mistakes it for Scripture:
  931. - **Tag.** Each corpus (or work) declares a `SourceTag` in the registry: canon
  932. status, kind, composition date, date tier (A: written before or alongside the
  933. NT; B: after the NT, to c. AD 200, with Targum Onkelos's later final form the
  934. stated exception), edition, and, where the copy is much
  935. later than the work, the manuscript date. 1 Enoch is dated book by book.
  936. The registry refuses a corpus with an untagged work.
  937. - **Caveat.** Each corpus declares a 1–3 sentence caveat, printed once per
  938. response that shows it (e.g. Philo: his Logos is not the incarnate Son).
  939. - **Editorial notes.** `src/study_bible_mcp/corpora/editorial_notes.json`
  940. (committed) holds verse-level notes — `emendation`, `interpolation`,
  941. `reconstruction`, `contrast`, `polemic`, `caution`, `gap` — with contrasting
  942. and aligned biblical references, and extra typed links. Each corpus import
  943. loads them into `ancient_source_notes` (one row per passage a citation
  944. covers; a `gap` note sits on the passages either side of its range) and
  945. fails if a citation covers no passage or a biblical reference does not
  946. parse. A file link to the same passage and range as a module link replaces
  947. it. Notes print as `⚠ <note> (Contrast: Mark 14:62)`, once per response.
  948. The file holds 46 notes and 40 links, e.g. Charles's emendation at 1 Enoch
  949. 71:14, the Christian "Jesus" of 4 Ezra 7:28–29, the restored lemma at 1QpHab
  950. 7:17, Philo's Logos at Conf. 146, and Yom Kippur atonement at m. Yoma 8:8–9.
  951. - **Typed links.** `ancient_source_biblical_links.relation` is `aligned`,
  952. `echo`, `shared_tradition`, `contrast`, or `translation`, printed as
  953. `Aligned: Jude 14–15 — …`, `Contrast: …` and so on. A pseudepigraphon is
  954. paired with the Scripture that takes it up (1 Enoch with Gen 6:1–4, Jude
  955. 6 and 14–15, 2 Pet 2:4, 1 Pet 3:19–20). Module links take `echo` when their
  956. note says the text cites, quotes or expounds the Bible and
  957. `shared_tradition` otherwise, unless they set a relation; `create_schema`
  958. adds the column to older databases with the same rule, and rebuilds an
  959. older search index.
  960. ### Josephus
  961. The `josephus` corpus uses all four Josephus works from
  962. [PerseusDL canonical-greekLit](https://github.com/PerseusDL/canonical-greekLit),
  963. pinned to commit `01b725d835e6e733062ffd79e0efdbae1ba06e5c`. The English TEI
  964. has one division per Whiston section, labelled with the Niese section where it
  965. starts; the Greek TEI has one division per Niese section. The importer joins
  966. every Greek section from each English start up to the next (the last section
  967. of a book runs to the book's last Greek section), so no Niese Greek is dropped;
  968. the later Greek book summaries (`arg`) are excluded. One mislabelled English
  969. division (Whiston 17.13.1, labelled `13`) is corrected to Niese 17.339 from the
  970. Greek milestone and text. Editor notes and Whiston's chapter headings are kept
  971. out of the primary-source text and the search index; headings are stored as
  972. editorial metadata. The FTS5 index uses Porter stemming for English and an
  973. accent-folded copy of the Greek. Each TEI file declares CC BY-SA 4.0; downloads
  974. are checked against their pinned Git blob hashes, and the build fails if any of
  975. the eight TEI files is missing.
  976. Biblical links are a small, separate editorial index of direct narrative
  977. overlap. Each targets a Niese section, attaches to the passage whose span
  978. contains it, and was checked against the passage text; the import fails if a
  979. link does not resolve. They do not assert literary dependence or historical
  980. agreement, and the Testimonium Flavianum link is marked as of disputed
  981. authenticity.
  982. ### Targums
  983. The `targum` corpus holds Targum Onkelos on all five books of the Torah, one
  984. work per book (`onkelos_genesis` … `onkelos_deuteronomy`, cited as `Onkelos
  985. Genesis 1:1` or `Tg. Onq. Deut 32:8`). The 10 version files come from Sefaria's
  986. archived export,
  987. [Sefaria/Sefaria-Export-Archive](https://github.com/Sefaria/Sefaria-Export-Archive)
  988. at commit `3f1013631fdfe452e953a93a2c5f921319e394ed` (the last commit holding
  989. the JSON texts), each checked against its pinned Git blob hash and against the
  990. `license` and `versionTitle` it declares; `merged.json` files are never used.
  991. - **Aramaic:** the Torat Emet text of Onkelos (Sefaria versions `Onkelos
  992. {Book}`), declared Public Domain by Sefaria. One passage per Sefaria verse
  993. (5,846). A `???` digitization mark before Genesis 49:12 is removed.
  994. - **English:** the Metsudah Chumash (Metsudah Publications, 2009, Sefaria
  995. version `Metsudah Chumash, Metsudah Publications, 2009 [with Onkelos
  996. translation]`, CC BY-NC 4.0). It translates the Hebrew text, so it is **not
  997. a direct translation of the Aramaic** beside it. Metsudah sets Onkelos's own
  998. renderings in bold (in Genesis 12–17, italic) brackets; these print as
  999. `⟨…⟩` (3,599 of them), while plain `[ ]` are Metsudah's own supplements,
  1000. e.g. Genesis 49:10 "until Shiloh Comes ⟨the Moshiach will come, for his is
  1001. the kingship⟩". The tag says "Metsudah: English of the Hebrew Torah;
  1002. ⟨marked⟩ words are Onkelos's renderings", and the licence line reads
  1003. `Aramaic text: Public domain; English translation: CC BY-NC 4.0`. A verse
  1004. without Metsudah English is an Aramaic-only passage.
  1005. **Versification.** Sefaria numbers Onkelos by the Hebrew verses; passages,
  1006. citations and links use the server's English numbering, with the Hebrew
  1007. number in the heading where it differs (`Targum Onkelos Exodus 8:5 (MT 8:1)`).
  1008. A static table in `targum.py` covers the Torah's 18 differing runs, as in
  1009. TAHOT's verses table (`Exo.8.5(8.1)`): Gen 31:55–32:32, Exod 8:1–32 and
  1010. 22:1–31, Lev 6:1–30, Num 16:36–17:13 and 29:40–30:16, Deut 12:32–13:18,
  1011. 22:30–23:25 and 29:1–29. Sefaria's Decalogue follows the upper accents, so
  1012. `Exodus 20:13–16` and `Deuteronomy 5:17–20` are one passage each and later
  1013. verses shift by three; `Numbers 26:1` also holds MT 25:19. The import fails if
  1014. the English keys stop rising.
  1015. Each passage has one editorial "Translation of" link to the English verse(s)
  1016. it covers, printed with the Hebrew number where it differs (`Translation of:
  1017. Exod 8:5 (MT 8:1)`), so `biblical_reference` finds Onkelos on a verse. The
  1018. period tag gives the redaction era (editorial): `amoraic`.
  1019. ### Qumran
  1020. The `qumran` corpus has one passage per manuscript column, its Hebrew lines
  1021. prefixed with their line numbers and cited `column:line`. No English
  1022. translation is included, so every passage is original-only and the tools say
  1023. so.
  1024. - **Damascus Document, Community Rule, Rule of the Congregation, Pesher
  1025. Habakkuk** (`CD`, `1QS`, `1QSa`, `1QpHab`): the Text-Fabric transcription by Martin G. Abegg Jr., James E.
  1026. Bowley and Edward M. Cook in [ETCBC/dss](https://github.com/ETCBC/dss),
  1027. release 2.0.1, pinned to commit `47ecc1738fad6e67df7d40a3e84d73e4a125e265`
  1028. and licensed [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/)
  1029. (checked in every feature file's header at download and import). CD keeps
  1030. the conventional page numbers: Genizah MS A columns 1–16 and MS B columns
  1031. 19–20, shown as `CD-A`/`CD-B` alongside, and its tag names the medieval copy
  1032. served (`copy: Cairo Genizah MS A, 10th c. AD`). Lines are rendered from the
  1033. sign-level features with the transcription's brackets: `[ ]` modern
  1034. reconstruction, `{ }` and `{{ }}` removal by a modern editor or the scribe,
  1035. `< >` and `<< >>` correction by a modern editor or the scribe, `^ ^`
  1036. supralinear, `( )` alternative reading, and `vacat` (spaced off from the
  1037. text) for an unwritten space.
  1038. A circlet above a letter (U+05AF) marks any of its four uncertainty
  1039. degrees, `◦` an unidentified sign, and `…` a missing sign; the morpheme
  1040. breaks Abegg inserts before suffixes are dropped, and the transcription's
  1041. `׃` marks are kept. Search ignores the circlets and indexes the corrected,
  1042. surviving reading: modern reconstruction in `[ ]` is never matched (the
  1043. letters either side of `יג[די]לו` are not joined into `יגלו`), and letters
  1044. in `{ }` and `{{ }}` and the word `vacat` are left out of the index
  1045. (`י{{א}}<<ע>>בורו` is found as `יעבורו`); the displayed text keeps every
  1046. sign. Other ETCBC scrolls are not imported (1QSb, for example, mixes
  1047. fragment labels and line gaps).
  1048. The 32 biblical links connect a 1QpHab column to each Habakkuk 1–2 verse
  1049. (range) whose lemma it quotes. Each was checked against the Masoretic verse,
  1050. and the import fails unless the anchor words survive outside the editor's
  1051. `[ ]` on their line. Three say how much of the lemma is restored; 7:14 links
  1052. Hab 2:4a only, "(end of 2:4a restored; 2:4b wholly reconstructed)".
  1053. R. H. Charles's public-domain English of the Damascus Document ("Fragments of
  1054. a Zadokite Work", *APOT* II, 1913) is not used. It is available only as OCR,
  1055. in Charles's own chapter:verse numbering with no Schechter page and line
  1056. references, and his chapter IX prints MSS A and B in parallel columns that the
  1057. OCR interleaves line by line, so it cannot be aligned reliably with CD lines.
  1058. ### Philo
  1059. The `philo` corpus uses the Greek (`grc1`, Cohn–Wendland–Reiter, *Philonis
  1060. Alexandrini opera quae supersunt*, Berlin: Reimer 1896–1915) and English
  1061. (`eng1`, C. D. Yonge, *The Works of Philo Judaeus*, London: Bohn 1854–55) TEI of
  1062. all 31 treatises in
  1063. [OpenGreekAndLatin/First1KGreek](https://github.com/OpenGreekAndLatin/First1KGreek)
  1064. (`data/tlg0018/tlg001`–`tlg031`, *De Opificio Mundi* to *Legatio ad Gaium*),
  1065. pinned to commit `03776b39f4047c5cff06f5296fae4b2bae4b08fb`. The module pins
  1066. each file's Git blob hash and fetches it from that commit without GitHub API
  1067. calls. The First1KGreek editors divided the English at the same Cohn–Wendland
  1068. sections as the Greek, so each passage is exactly one section: its Greek and
  1069. the English section of the same number, never a neighbouring one. The 58
  1070. Greek sections of *Spec.* 1.177–193 and 2.124–213 that Yonge's shorter text
  1071. lacks are imported as Greek-only passages, marked "Yonge has no English for
  1072. this section"; an English section without a Greek counterpart fails the
  1073. import. Apparatus, marginal notes, page and line markers,
  1074. and Yonge's footnotes and source references are kept out of the text; Yonge's
  1075. treatise headings (e.g. "A TREATISE ON CIRCUMCISION." within *Spec.*) are
  1076. editorial headings. Each file declares CC BY-SA 4.0, checked at download and
  1077. parse. Works surviving only in Armenian or Latin (*QG*, *QE*, *Prov.*, *Anim.*),
  1078. the *Hypothetica*, and fragments are not in First1KGreek and are not included.
  1079. Twenty-five curated links name the Genesis or Exodus verse a section quotes and
  1080. expounds (e.g. *Leg.* 1.31 → Gen 2:7) and *Legat.* 299 → Luke 3:1 (Pilate).
  1081. Search for Philo's Greek uses Greek script (`λόγος`, `λογος`); a transliteration
  1082. such as `logos` does not match, and Yonge renders λόγος as "word" or "reason".
  1083. ### Pseudepigrapha
  1084. The `pseudepigrapha` corpus holds two non-canonical works. **1 Enoch** is R. H.
  1085. Charles's translation (2nd ed. 1912, SPCK reprint 1917) from English Wikisource,
  1086. one page per chapter (1–108), each pinned to a revision id and its SHA-1 and
  1087. fetched in three MediaWiki API requests. The translation is in the public domain
  1088. in the United States (Charles died in 1931; Wikisource `{{PD/US|1931}}`). Each
  1089. passage is one Charles verse in his order, including his sub-verses and
  1090. transpositions (`1 Enoch 5:6a–b`, `5:7c`, `5:6d–j`; `89:48b`; `91:14d`), all
  1091. sorted under their verse number; Charles's section headings
  1092. (`LXXXIX. 72-77. ...`) are editorial headings. Where Charles prints a parallel
  1093. column with a header (his rendering of the Greek or Latin witnesses in chapters
  1094. 22, 27, 32, 89, and 106) only the main Ethiopic column is imported; the
  1095. unheaded doublet columns of 90:13–18 are both text. No Ge'ez is included: the
  1096. Beta maṣāḥǝft file (`LIT1340EnochE`) offers Dillmann's text only at chapter
  1097. level under a custom non-commercial notice that must accompany every copy, and
  1098. an EOTC printed-edition text whose own rights are not stated.
  1099. **4 Ezra** is 2 Esdras 3–14 in the KJV with Apocrypha (eBible.org `eng-kjv`,
  1100. public domain; the extracted `58-2ESeng-kjv.usfm` is pinned by SHA-256 because
  1101. eBible regenerates its zip) paired with the Clementine Vulgate's *Liber Quartus
  1102. Esdrae* (Rome 1598) from Latin Wikisource revision 148869 (transcribed from
  1103. public-domain page images; Wikisource transcription CC BY-SA 4.0, credited by
  1104. URL in every Sources block). Passages are
  1105. one KJV verse with the Latin verse of the same number, except 27 spans where
  1106. the two divide verses differently (usually a speech introduction such as "Et
  1107. dixit ad me," / "And he said unto me" placed on the other side of a verse
  1108. boundary, and an offset in 14:14–20); each span pairs all of its English with
  1109. all of its Latin, and the import fails if any verse of either text is left
  1110. unpaired. 4 Ezra 3–14 keeps the 2 Esdras chapter numbers; KJV 7:36–70 is
  1111. cited as 7:106–140 (both texts lack the "missing fragment" 7:36–105, which is
  1112. not available from an openly licensed source). 2 Esdras 1–2 and 15–16 are later
  1113. Christian additions (5 and 6 Ezra) and are not included. A citation outside
  1114. the served text (`4 Ezra 7:50`, `2 Esdras 15:1`) says both.
  1115. Period tags give conventional composition dates (1 Enoch: Watchers,
  1116. Astronomical Book, Dream Visions, and Epistle `hellenistic`, Parables `roman`;
  1117. 4 Ezra `roman`, after 70 CE). Twenty-two curated links mark allegorical
  1118. retellings and shared imagery, e.g. the Animal Apocalypse (1 Enoch 89) with the
  1119. Genesis–Kings narrative and Malachi 1:7, and the eagle vision (4 Ezra 11–12)
  1120. with Daniel 7, which 4 Ezra 12:11 names; 1 Enoch 1:9 → Jude 14–15 and 6:1 →
  1121. Gen 6:1–2 are `aligned`. The editorial-notes file adds the aligned links to
  1122. Jude 6, 2 Pet 2:4 and 1 Pet 3:19–20.
  1123. ### Rabbinic texts
  1124. The `rabbinic` corpus holds the Mishnah from Sefaria's JSON export, pinned to
  1125. commit `3f1013631fdfe452e953a93a2c5f921319e394ed` of
  1126. [Sefaria/Sefaria-Export-Archive](https://github.com/Sefaria/Sefaria-Export-Archive)
  1127. (the last full export committed before Sefaria moved it to a GCS bucket that
  1128. is overwritten monthly and not versioned) and verified by Git blob hash. Every
  1129. Sefaria version declares its own licence; downloads and imports reject any
  1130. version that is not Public Domain or CC-BY. CC-BY is recorded as CC BY 3.0,
  1131. the licence Sefaria's reader links it to.
  1132. - **Mishnah**, all 63 tractates, one passage per mishnah (`Mishnah Shekalim
  1133. 1:1`): Hebrew *Mishnah, ed. Romm, Vilna 1913* (public domain) with Joshua
  1134. Kulp's *Mishnah Yomit* English (CC BY). Bikkurim chapter 4, absent from the
  1135. Vilna version, is English only.
  1136. Footnotes, footnote markers and HTML are removed from the English. Curated
  1137. links: Mishnah Shekalim 1:1 and 1:3 to Matthew 17:24–27 (the half-shekel); the
  1138. editorial-notes file adds Gospel echoes (e.g. Shekalim 1:3 → Mark 11:15) and
  1139. contrast notes. The corpus caveat warns that Kulp's bracketed Bible references
  1140. sometimes use Hebrew numbering or contain errors.
  1141. ### BDB Hebrew Lexicon
  1142. The full unabridged Brown-Driver-Briggs Hebrew lexicon (8,090 entries) comes from [eliranwong/unabridged-BDB-Hebrew-lexicon](https://github.com/eliranwong/unabridged-BDB-Hebrew-lexicon). The BDB is the standard scholarly Hebrew-English lexicon, originally published in 1906 and still widely used in academic study. Public domain text.
  1143. ### Abbott-Smith Greek Lexicon
  1144. G. Abbott-Smith's *A Manual Greek Lexicon of the New Testament* (1922) provides NT-focused definitions that complement the broader classical coverage of LSJ. The TEI XML edition (5,896 entries) comes from [translatable-exegetical-tools/Abbott-Smith](https://github.com/translatable-exegetical-tools/Abbott-Smith). Public domain text.
  1145. Abbott-Smith enriches 5,426 existing Greek entries with:
  1146. | Field | Description | Coverage |
  1147. |-------|-------------|----------|
  1148. | **NT-focused definition** | Full definition with sense hierarchy | 5,871 entries |
  1149. | **NT occurrence count** | Word frequency in the New Testament | 5,480 entries |
  1150. | **LXX/Hebrew equivalents** | Hebrew words the Greek translates in the Septuagint | 3,317 entries |
  1151. | **Synonym discussions** | Scholarly notes distinguishing related Greek words | 398 entries |
  1152. ### BibleAquifer
  1153. Scholarly commentary and reference content from [BibleAquifer](https://github.com/BibleAquifer) (CC BY-SA 4.0):
  1154. | Resource | Description | Content |
  1155. |----------|-------------|---------|
  1156. | **Aquifer Open Study Notes** | Verse-level scholarly commentary | 66 books |
  1157. | **Tyndale Bible Dictionary** | Topical articles | 500+ articles on people, places, theology, history, archaeology |
  1158. | **UW Translation Notes** | unfoldingWord translator commentary | Linguistic insights for 49+ books |
  1159. | **SIL Translator Notes** | SIL International translator notes | Translation and cultural context |
  1160. | **FIA Key Terms** | Key theological terms | 200+ carefully defined terms with cross-references |
  1161. ### ACAI Entity Annotations
  1162. Rich entity annotations from [BibleAquifer/ACAI](https://github.com/BibleAquifer/ACAI) (CC BY-SA 4.0):
  1163. | Type | Count | Content |
  1164. |------|-------|---------|
  1165. | People | 3,426 | Family relationships, variant names, roles, speech attributions, verse references |
  1166. | Places | 1,418 | Geographic entities with biblical references |
  1167. | Groups | 307 | People groups, nations, tribes |
  1168. | Key Terms | 868 | Annotated theological concepts |
  1169. ### Theographic Bible Metadata
  1170. Graph data for genealogy, events, and places from [Theographic](https://github.com/robertrouse/theographic-bible-metadata), with curated corrections and twenty added events (the binding of Isaac, the burning bush, the fall of Jerusalem ...) in [`src/study_bible_mcp/parsers/graph_curated.json`](src/study_bible_mcp/parsers/graph_curated.json). Used by the `explore_genealogy`, `explore_person_events`, `explore_place`, `find_connection`, `people_in_passage`, and `graph_enriched_search` tools.
  1171. ### Torah Weave
  1172. `get_torah_weave` reads version 1.1 of Moshe Kline's Torah Literary Units
  1173. dataset ([chaver.com](https://chaver.com/torah-weave/data/torah-units.json),
  1174. CC BY 4.0; Kline, *Before Chapter and Verse: Reading the Woven Torah*, 2022):
  1175. 86 units of Genesis–Deuteronomy with 600 cells, 1,019 counting subdivisions.
  1176. The file ships as `data/torah_weave/torah-units.json`. Its URL is unversioned,
  1177. so it is pinned by SHA-256 (`TORAH_WEAVE_SHA256` in
  1178. `src/study_bible_mcp/parsers/torah_weave.py`, the file retrieved on
  1179. 2026-10-14), and the import fails on any other file. Kline numbers verses like
  1180. the Hebrew Bible (Leviticus 5:20-26 is English 6:1-7); the tool takes and shows
  1181. English numbers. Every Torah verse is in a cell except Deuteronomy 5:30-33,
  1182. which sit in unit 76 without one, and Exodus 20:23-26, which no unit includes.
  1183. ### Ancient Near East Context
  1184. 87 structured entries covering 12 dimensions of ANE cultural and historical context across 9 time periods, with 314 book-chapter mappings. Data is stored in [`data/ane_context/`](data/ane_context/) as JSON files (one per dimension). Sources include Walton, Hallo, Matthews & Benjamin, Pritchard (ANET), and other standard ANE reference works.
  1185. ### Theological Scholarship
  1186. 193 verse-anchored entries covering Heiser, Bradley, Burnett, Owen, Stott, and Lennox, served by `get_theology_context`.
  1187. These entries are **original summary prose written for this database**, describing each author's argument on a passage or theme with attribution. They are not reproduced text from the authors' works. The material was derived from publicly available research and teaching — papers, articles, lectures, and podcasts — rather than from in-copyright books; where a specific public source is known, the entry carries its URL and the tool output shows it. Every result from `get_theology_context` states this provenance inline.
  1188. John Owen (d. 1683) is in the public domain, so those entries are cited directly by work.
  1189. #### Source links
  1190. An entry's `url` is shown as **Source URL** in `get_theology_context` output. Links are added only where the source itself is legitimately free online:
  1191. | Author | Link target |
  1192. |---|---|
  1193. | Owen | Free public-domain text: the [CCEL](https://ccel.org/ccel/owen) chapter or part the entry draws on (Communion with God, The Death of Death, The Glory of Christ, Justification, Mortification, Indwelling Sin); for the Exposition of Hebrews, which CCEL lacks, the Monergism PDF of the volume covering that chapter |
  1194. | Heiser | His papers on thedivinecouncil.com / drmsh.com / Liberty Digital Commons, and Naked Bible podcast transcripts |
  1195. | Burnett | His own serialisation of the argument on drmsh.com (based on his SBL paper); the JSPL article itself is not openly hosted |
  1196. | Bradley, Stott, Lennox | None: no free copy hosted by the author or publisher |
  1197. In the content JSON, a file-level `url` applies to every entry; an entry-level `url` (for example a chapter page) overrides it.
  1198. #### Applying data changes to an existing database
  1199. The importers are re-runnable. A row that already exists (same `source_work`, `chapter_or_episode`, `title`) is not duplicated and keeps its content; only its `url` is refreshed. To apply new or corrected links to an existing DB:
  1200. ```bash
  1201. DB=db/study_bible.db
  1202. python scripts/relabel_theology_sources.py $DB # no-op if already relabelled
  1203. python scripts/import_heiser_content.py $DB
  1204. python scripts/import_bradley_content.py $DB
  1205. python scripts/ingest_reformed_evangelical.py $DB # Owen, Stott, Lennox
  1206. python scripts/ingest_burnett_gage.py --theology-only $DB
  1207. python scripts/dedupe_theology_theme_links.py $DB # no-op once clean
  1208. ```
  1209. The relabel step must come first on a DB built before the descriptive labels: the data files now use those labels as `source_work`, so an unrelabelled DB would not match and would gain duplicate rows. The dedupe step removes theme links that earlier importer runs duplicated (their NULL `reference` slipped past the UNIQUE constraint), which inflated theme entry counts.
  1210. ### Ancient Near East Context
  1211. The 87 ANE entries are likewise original summary prose describing scholarly consensus on ANE background, with the standard reference works named as sources rather than quoted.
  1212. ### Vector Embeddings
  1213. Semantic search uses OpenAI's `text-embedding-3-small` model via [sqlite-vec](https://github.com/asg017/sqlite-vec) for the `find_similar_passages` tool.
  1214. ---
  1215. ## Contributing
  1216. Contributions welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for setup, the test
  1217. suite (run in CI on every pull request) and the rules every change keeps:
  1218. small outputs, Scripture kept distinct from other sources, pinned and licensed
  1219. data, and safe database upgrades. Especially welcome:
  1220. - Additional thematic cross-references
  1221. - Improved genre detection
  1222. - New translation support
  1223. - Better morphology parsing
  1224. - Documentation improvements
  1225. ---
  1226. ## License
  1227. MIT License. See [LICENSE](LICENSE).
  1228. Data from STEPBible is licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).
  1229. OpenScriptorium LXX morphology and MT/LXX verse mappings (derived in part from STEPBible's TVTMS) are licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); the Rahlfs Greek text and Brenton's English translation and Greek text are public domain.
  1230. The Perseus Josephus Greek and English TEI editions are licensed under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/).
  1231. The Onkelos Aramaic (Torat Emet) is public domain as declared by [Sefaria](https://www.sefaria.org/); the Metsudah Chumash English of Onkelos is licensed under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) (non-commercial use only), and its licence is shown on every passage.
  1232. The ETCBC/dss Dead Sea Scrolls transcription (Abegg, Bowley and Cook), the source of all four Qumran texts, is licensed under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) (non-commercial use only).
  1233. The First1KGreek Philo Greek and English TEI editions are licensed under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/); Cohn–Wendland's Greek and Yonge's English are public domain.
  1234. Charles's 1 Enoch (via English Wikisource) and the KJV 2 Esdras (via eBible.org) are public domain; the Latin Wikisource transcription of the Clementine 4 Esdras is licensed under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/).
  1235. Mishnah passages carry each version's licence: Kulp's Mishnah Yomit English is CC BY, and the Vilna Mishnah is public domain.
  1236. Data from BibleAquifer and ACAI is licensed under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/).
  1237. Torah Weave data (version 1.1) from Moshe Kline ([chaver.com](https://www.chaver.com/)) is licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).
  1238. BDB, Abbott-Smith, the Treasury of Scripture Knowledge, and the works of John Owen are public domain.
  1239. The theology and ANE entries are original summary prose written for this project — see [Data Sources](#data-sources).
  1240. ---
  1241. ## Acknowledgments
  1242. - [STEPBible](https://www.stepbible.org/) for the freely available biblical data
  1243. - [OpenScriptorium](https://github.com/OpenScriptorium/lxx-morph) for Rahlfs LXX morphology and explicit MT/LXX verse mappings
  1244. - [STEPBible.org / Tyndale House Cambridge](https://github.com/STEPBible/STEPBible-Data) for TVTMS, the versification data behind those mappings
  1245. - [eBible.org](https://ebible.org/details.php?id=eng-Brenton) for the public-domain Brenton Septuagint, English and [Greek](https://ebible.org/details.php?id=grcbrent)
  1246. - [Perseus Digital Library](https://github.com/PerseusDL/canonical-greekLit) for the licensed Josephus Greek and English editions
  1247. - [Sefaria](https://www.sefaria.org/) for the Torat Emet text of Onkelos and the Metsudah Chumash English, via [Sefaria-Export-Archive](https://github.com/Sefaria/Sefaria-Export-Archive)
  1248. - [ETCBC/dss](https://github.com/ETCBC/dss) and Martin G. Abegg Jr., James E. Bowley and Edward M. Cook for the Dead Sea Scrolls transcription
  1249. - [Open Greek and Latin / First1KGreek](https://github.com/OpenGreekAndLatin/First1KGreek) for the licensed Philo Greek and English editions
  1250. - [Wikisource](https://en.wikisource.org/wiki/The_Book_of_Enoch_(Charles)) contributors for R. H. Charles's 1 Enoch and the [Latin Clementine Vulgate](https://la.wikisource.org/wiki/Vulgata_Clementina) 4 Esdras
  1251. - [eBible.org](https://ebible.org/find/show.php?id=eng-kjv) for the public-domain KJV with Apocrypha
  1252. - [Sefaria](https://www.sefaria.org/) for the Vilna Mishnah and Joshua Kulp's Mishnah Yomit English
  1253. - [BibleAquifer](https://github.com/BibleAquifer) for study notes, dictionary, translation notes, and key terms
  1254. - [eliranwong](https://github.com/eliranwong/unabridged-BDB-Hebrew-lexicon) for the unabridged BDB Hebrew lexicon
  1255. - [translatable-exegetical-tools](https://github.com/translatable-exegetical-tools/Abbott-Smith) for the Abbott-Smith Greek Lexicon TEI XML edition
  1256. - [Theographic](https://github.com/robertrouse/theographic-bible-metadata) for genealogy and event graph data
  1257. - Gordon Fee & Douglas Stuart for the hermeneutical framework in "How to Read the Bible for All Its Worth"
  1258. - The MCP community for the protocol and tooling

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.