bible-mcp

An MCP server for Christian scholarship and research. Non-commercial, aiming to become a public resource. See corpus-survey.md for the full source/license landscape and ROADMAP.md for direction.

What's in it (v0.14)

| Data | Source | License | |---|---|---| | Berean Standard Bible (66 books) | berean.bible | Public Domain | | World English Bible, Ecumenical (83 books incl. Apocrypha) | ebible.org | Public Domain | | Septuagint (Brenton translation, 1851) — OT + Apocrypha, incl. Susanna/Bel and the Dragon/Epistle of Jeremiah as separate books; Psalms remapped to standard English/KJV numbering (LXX's own numbering diverges throughout most of the Psalter — verified verse-by-verse against WEB); Jeremiah, Daniel-Greek, Exodus, Job, Esther-Greek, and Baruch retain Brenton's native LXX chapter/verse structure, which differs from BSB/WEB in these books (reordering and/or length, not just numbering) | ebible.org | Public Domain | | Septuagint, Greek text (Swete edition, Cambridge 1887–1894) — Genesis through Malachi plus Apocrypha, Theodotion Daniel/Susanna/Bel; same Psalms remap and native-structure caveats as the English Brenton text above. Word-level (surface form only, no lemma/Strong's/morphology), powers get_interlinear alongside the Hebrew/Aramaic OT and Greek NT | Open Greek and Latin Project / First1KGreek, via github.com/nathans/lxx-swete | CC BY-SA 4.0 | | 613,690 original-language words: Greek NT + Hebrew/Aramaic OT with lemmas, Strong's, morphology, glosses, semantic domains | MACULA (Clear-Bible/Biblica) | CC BY 4.0 | | Brown-Driver-Briggs Hebrew and English Lexicon (1906, 9,290 entries) + Strong's Hebrew Dictionary (1890, revised, 8,674 entries) — full scholarly entries (etymology, sense divisions, verse citations) keyed by Strong's number, including BDB's own lettered homographs (e.g. H2617a "lovingkindness" vs H2617b "reproach" — genuinely different words, same spelling); surfaces in word_study alongside the existing short gloss | OpenScriptures HebrewLexicon | CC BY 4.0 (markup; underlying BDB/Strong's text is Public Domain) | | Abbott-Smith's Manual Greek Lexicon of the New Testament (1922, 517 entries) — same treatment for Greek NT words | First1KGreek / Open Greek and Latin Project, via github.com/biblicalhumanities/Abbott-Smith | Public Domain | | ~345,000 ranked cross-references | openbible.info | CC BY | | ~4,800 people/places/events/groups + 53,000 verse links | Theographic Bible Metadata | CC BY-SA 4.0 | | Six PD classics: Augustine's Confessions, Imitation of Christ, Pilgrim's Progress, Practice of the Presence of God, Julian's Revelations, Chesterton's Orthodoxy | Project Gutenberg | Public Domain | | The Apostolic Fathers, ten works: 1 & 2 Clement, Epistle of Barnabas, Polycarp to the Philippians, Martyrdom of Polycarp, Epistles of Ignatius (shorter recension), Martyrdom of Ignatius, Epistle to Diognetus, Pastor of Hermas, Fragments of Papias | ANF (Roberts-Donaldson-Crombie), Project Gutenberg #77576 | Public Domain | | Irenaeus: Against Heresies, Books I–V + Fragments — 806 sections addressed as IREN-AH<book>.<chapter>.<section> so standard citations (AH 3.3.4) resolve directly; 1,598 tier-1 scripture citations | ANF vol. I (Roberts-Rambaut), Wikisource transcription | Public Domain | | Justin Martyr: First Apology, Second Apology, Dialogue with Trypho, Martyrdom of Justin — 423 sections, ~408 tier-1 citations | ANF vol. I, Wikisource transcription | Public Domain | | Tier-1 citation graph: scripture citations extracted from the translators' own footnotes across the patristic shelf (see DESIGN.md §4) | — | — | | Versemap: 988 empirically derived MT/NA ↔ English verse alignments across 31 books (Joel 2–4, Malachi 3–4, Hosea, Isaiah 64, Kings/Chronicles/Nehemiah seams, 3 John, Acts 19, Rev 12…), gloss-validated; plus the Psalms superscription offsets | derived from corpus | — | | Research outputs layer (layer='output'): Layer 0 corpus surveys + Layer 2 research briefs for potter-and-clay, living water, wilderness — searchable, embedded, with draws_on links back to their grounding refs | generated in-project | — | | ~112,400 embeddings (verse/window/paragraph) for semantic + hybrid search across every layer | bge-small-en-v1.5, generated locally | — | | Easton's Bible Dictionary (1897 3rd edition, 2,491 entries) — a full corpus document like the PD classics above: searchable (search(version="EASTON")), readable (read_work("EASTON", ...)), embedded for semantic search | Theographic's structured JSON re-derivation | Public Domain | | OT+NT concept graph: 5,673 concept nodes (theological themes + lexical keywords, seeded from Easton's Bible Dictionary) and 171,000+ typed/associated edges (broader/narrower/causes/part_of/symbol_of/fulfills/associated) linking concepts to each other, to entities, and to verse anchors across both Testaments; ~440 typed edges hand-reviewed against cited evidence (Phase 5/6), the rest mechanical associated overlap counts. Live via get_concept/concepts_in_passage/get_concept_relations, see DESIGN.md §5 | derived from corpus + Easton's Bible Dictionary | — |

All in one SQLite file (db/bible.db, ~400MB) with FTS5 full-text search. Prose works are addressed as WORK.chapter.paragraph. See DESIGN.md for the architecture rationale.

Tools

• get_passage(reference, version="BSB") — Bible text for a reference, e.g. John 3:16, John 3:16-18, Genesis 1. Versions: BSB, WEB (Apocrypha requires version="WEB").
• search(query, version="BSB", book="", limit=20) — Full-text search, stemmed and ranked (BM25). Supports quoted phrases and AND/OR/NOT, e.g. faith AND works NOT law. version also takes any prose work id. Note: stemming conflates related surface forms (e.g. "desert" also matches "deserted") — quote exact phrases or add AND-terms to disambiguate.
• semantic_search(query, top_k=12, kind="", hybrid=True) — Meaning-based search across the whole corpus (scripture + prose), hybrid-fused with keyword search (RRF) by default. Finds passages on a theme even with no shared words, e.g. "divine self-emptying". kind optional: verse | window | paragraph.
• find_similar(reference, top_k=10) — Nearest passages by embedding to a given verse or prose paragraph, across scripture, Apocrypha, and the classics. Powers parallel-finding across corpus layers.
• word_study(query, language="", limit=15) — Original-language word study by Strong's number (zero-padding optional), lemma (pointed or unpointed), Hebrew/Aramaic transliteration (e.g. miqweh, macrons optional), or English gloss. Returns occurrence counts, gloss range, book distribution, a full scholarly lexicon entry when available (BDB/Strong's for Hebrew, Abbott-Smith for Greek — richer than the gloss, truncated to ~700 chars), and sample verses. Lettered homograph variants (e.g. H4723 vs H4723a — same written form, different word) are surfaced together. language optional: grc | hbo | arc.
• get_interlinear(reference) — Word-by-word original language for a verse or short range: surface form, lemma, Strong's, gloss, morphology (Hebrew/Aramaic OT, Greek NT). Versemap-corrected across all books, not just Psalms. For OT verses also shows Septuagint Greek surface text where available (no lemma/Strong's/morphology in that source).
• get_cross_references(reference, limit=20) — Cross-references for a verse (OpenBible.info, ranked by community votes), with the target text included.
• get_citations(reference, limit=20) — Where a verse is cited by name in the patristic corpus, extracted from the translators' own footnotes (tier 1). Complements get_cross_references (scripture→scripture); this is patristic text→scripture. Coverage is sparse by design — an empty result doesn't mean uncited; full-text search within the patristic works is the thorough probe.
• get_entity(name, entity_type="") — Look up a biblical person, place, event, or people group by name (Theographic knowledge graph); returns details and where they appear. entity_type optional: person | place | event | people_group.
• entities_in_passage(reference) — People, places, and events linked to a verse or chapter, e.g. Genesis 14.
• get_concept(name, concept_type="") — Look up a theological concept or lexical keyword in the OT+NT concept graph (seeded from Easton's Bible Dictionary); returns its definition, verse anchors, instantiating entities, and a relation-count summary. concept_type optional: theme | keyword. Also accepts a Strong's number.
• concepts_in_passage(reference) — Theological concepts and keywords linked to a verse or chapter, e.g. Genesis 15. Complements entities_in_passage.
• get_concept_relations(name, verb="", limit=20) — Typed relations for a concept: broader/narrower/causes/part_of/symbol_of/fulfills/contrasts, hand-reviewed against cited evidence. Excludes the much larger mechanical associated tier by default — pass verb="associated" to include it.
• read_work(work, chapter=1, start=1, end=5) — Read a prose work by paragraph range (CONFESSIONS, IMITATION, PILGRIM, PRESENCE, JULIAN, ORTHODOXY, 1CLEMENT, BARNABAS, EASTON, and others — see corpus_info() for the full list). Use search(version=<WORK>) to find passages first.
• compare_versions(reference) — A verse or short range in BSB and WEB, side by side.
• corpus_info() — What's in the corpus: documents, layers, licenses, and counts.

Prompts

The server also exposes the synthesis pipeline as MCP prompts, generated from .claude/skills/ (the source of truth): corpus_survey(theme) — Layer 0 raw reading discipline; corpus_composer(theme) — Layer 2 research-brief composition. Any MCP client that installs bible-mcp gets the discipline bundled with the data.

Setup

pip install -r requirements.txt   # core: just `mcp`
pip install fastembed numpy       # optional semantic tier (semantic_search, find_similar)
python3 scripts/build_db.py       # rebuild db from data/sources (optional; db ships built)
python3 scripts/embed.py          # regenerate embeddings (optional; ships built; resumable)

The first semantic query downloads the embedding model (~65MB, one time). Without fastembed/numpy installed, all non-semantic tools work normally. See DESIGN.md for architecture decisions (model choice, chunking, hybrid retrieval).

Claude Desktop / Cowork — add to MCP config:

{
  "mcpServers": {
    "bible-mcp": {
      "command": "python3",
      "args": ["/path/to/bible-mcp/server.py"]
    }
  }
}

Layout

data/sources/   raw acquired sources (immutable; re-derive, never edit)
data/versemap.tsv        derived MT/NA <-> English verse alignments
data/additions-*.json    prepared incremental ingestions (applied via scripts/ingest_additions.py)
scripts/        schema.sql, lib_refs.py, build_db.py, build_versemap.py, align_splits.py, ingest_additions.py
db/bible.db     the built corpus (SQLite + FTS5)
outputs/        synthesis-pipeline artifacts (Layer 0 surveys, Layer 2 briefs, reports)
.claude/skills/ corpus-survey + corpus-composer (pipeline skills; source for MCP prompts)
server.py       MCP server (FastMCP, read-only on the db)

Public edition

This is a non-commercial public resource. Licensing is layered — sources keep their own licenses (all PD / CC BY / CC BY-SA); the code is PolyForm Noncommercial 1.0.0; the compilation and derived data (versemap, citation graph, embeddings, outputs layer) are CC BY-NC 4.0. Full details: LICENSE.md, attributions in NOTICE.md.

Three ways to use it:

1. Remote (no install) — add the hosted endpoint as a custom connector in any MCP client (Claude: Settings → Connectors → Add custom connector): https://bible-mcp-server.fly.dev/mcp
2. Local (stdio) — clone, download db/bible.db from the latest GitHub Release (or rebuild from data/sources/), add the config above.
3. Self-host — Dockerfile