Skip to main content
Glama

local-bible-library

An owned, verifiable Bible study library on your own disk, with tools for the terminal and for Claude (via MCP).

Commercial Bible software rents you a library that its servers can revoke, alter, or lock. This project builds the opposite: open-licensed sources downloaded straight from their publishers, kept byte-for-byte as published, proven unchanged by hash, and indexed so that scripts and AI assistants can query them without ever being able to change them.

Principles

  1. Sources are never modified. Every download is hashed, recorded in a committed manifest, and locked read-only. Nothing (no script, no LLM, no import step) writes into a source after ingest. New upstream releases go into a new version directory; old ones are kept.

  2. Download, don't distribute. This repository holds code, recipes and manifests only. lbl ingest fetches each source from its publisher. No source data is redistributed here.

  3. Everything derived is rebuildable and labeled. The search index is a cache built from the library. Every row records where it came from and whether it is verbatim source text, a deterministic parse, or machine output (OCR, LLM).

  4. Reference, not interpretation. The tools surface texts, lexicons, commentaries and data. AI is used as a clerk that fetches and cites, never as an authority.

Related MCP server: bible-translation-mcp

Status

Early. See the milestones for the roadmap.

Milestone

Scope

M0 Foundation

Integrity layer (ingest, verify, locks), repo conventions

M1 Core data

STEPBible-Data, OpenBible, BSB; build the SQLite index

M2 Access

CLI and MCP server

M3 Library

Public-domain commentaries, modern open resources, church fathers

M4 Notes

Verse-referenced Markdown notes indexed alongside sources

M5 Readers and local models

Ezra, STEPBible desktop, LM Studio, semantic search

M6 Language growth

Vocabulary, reader's editions, guided morphology

Quick start

Requires uv and git.

uv sync
uv run lbl status          # recipes and what is ingested
uv run lbl ingest <id>     # fetch, hash, lock, write manifest
uv run lbl verify          # prove library/ matches the manifests

Commit the new file under manifests/ after every ingest. A manifest only protects anything once it is in git history.

Studying

uv run lbl build                       # verify, then rebuild the index (about 10 seconds)
uv run lbl verify-db                   # re-derive every index row from its source line
uv run lbl passage John 1:1-5 -i       # text, original language, word by word
uv run lbl word G26                    # lexicon, occurrences, renderings, forms
uv run lbl word reshit                 # by transliteration or lemma
uv run lbl search "living water"       # translation, lexicon and original text
uv run lbl xrefs Rom 8:28              # cross-references ranked by votes
uv run lbl commentary John 3:16 -m RWP # what each commentary says (--list for modules)
uv run lbl fathers John 1:1            # church fathers on a passage, oldest first
uv run lbl notes John 1:1              # unfoldingWord translation notes on each Greek/Hebrew phrase
uv run lbl dict Bethel                 # Easton, ISBE, Smith, Nave, Abbott-Smith, ... (--list)
uv run lbl quote "In the beginning was the Word"   # exact, normalized or not found
uv run lbl sql "SELECT ..."            # read-only SQL; see docs/SCHEMA.md

Every command takes --json, and every result carries a citation: source@version:file:line.

With Claude (MCP)

.mcp.json registers a read-only MCP server named bible (uv run lbl mcp). Claude Code asks once to enable it. It provides the tools passage, word, search, xrefs, commentary, commentary_modules, church_fathers, translation_notes, dictionary, dictionary_modules, check_quote, sql, schema and sources, and the prompts /passage_guide and /word_study. The server instructs Claude to quote only tool output, cite every quotation, confirm quotes with check_quote, and keep interpretation separate and labeled.

Layout

sources/<id>.toml              recipe: where a source comes from, its license   (committed)
manifests/<id>/<version>.toml  what was ingested: every file's SHA-256           (committed)
library/<id>/<version>/        the source itself, as published, locked          (never committed)
build/                         derived index, rebuildable                       (never committed)
notes/                         your study notes, a separate private repo        (never committed here)
src/lbl/                       the tooling
docs/                          INTEGRITY.md, SOURCES.md

Licenses

The code in this repository is MIT licensed. Each source keeps its own license, recorded in its recipe and manifest; check it before you share anything built from it.

Available Tools

14 tools
check_quoteA
Read-onlyIdempotent

Check a quotation against the sources. verdict 'exact' = appears verbatim; 'normalized' = matches only if accents, punctuation and case are ignored (so it was altered); 'not_found'.

Inputs: text (required).

church_fathersA
Read-onlyIdempotent

Church fathers and other historical writers on a passage (ANF/NPNF and similar, from the Historical Christian Faith database), oldest first, each quote with its work and citation. author filters by name substring (e.g. 'Augustine', 'Chrysostom').

Inputs: ref (required), author, max_chars.

commentaryA
Read-onlyIdempotent

What each public-domain commentary in the library (Matthew Henry, JFB, Barnes, Clarke, Keil and Delitzsch, Calvin, Robertson's Word Pictures, ...) says on a passage, quoted with citations. Notes covering several verses are filed under the first; entries marked nearest_preceding may cover the verse asked about. modules limits the set (names from commentary_modules).

Inputs: ref (required), modules, max_chars.

commentary_modulesA
Read-onlyIdempotent

Commentary modules in the library with entry counts and licenses.

Inputs: no named parameters.

dictionaryB
Read-onlyIdempotent

Look up a headword or Strong's number in the dictionaries and lexicons in the collection: Easton, ISBE, Smith, Nave, Torrey, Hitchcock (topics, people, places) and Abbott-Smith, Dodson, Strong's, BDB glosses (Greek and Hebrew words). Falls back to full-text search when no headword matches.

Inputs: term (required), modules, max_chars.

dictionary_modulesB
Read-onlyIdempotent

Dictionary and lexicon modules with entry counts and licenses.

Inputs: no named parameters.

passageA
Read-onlyIdempotent

Verse text (BSB) and original-language text for a reference such as 'John 3:16', 'Rom 8:28-30' or 'Ps 23'. With interlinear=true, each word with transliteration, gloss, Strong's number, lemma, lexicon gloss and parsed morphology. Every text carries its source citation.

Inputs: ref (required), interlinear.

schemaA
Read-onlyIdempotent

The index schema (CREATE statements) and the design notes from docs/SCHEMA.md.

Inputs: no named parameters.

sourcesB
Read-onlyIdempotent

Sources in the index with versions and licenses, row counts, and whether the library currently verifies against its manifests and matches the index.

Inputs: no named parameters.

sqlA
Read-onlyIdempotent

Read-only SQL (SQLite) against the index, for questions the other tools don't cover, such as morphology patterns. Call schema first. Only SELECT is permitted; results are capped at 200 rows. Hebrew verb stems are the second letter of segment.morph for verbs (e.g. 'Vh%' = hiphil); Greek parsing codes look like 'V-AAM-2S' (aorist active imperative).

Inputs: query (required).

translation_notesA
Read-onlyIdempotent

unfoldingWord Translation Notes (CC BY-SA) on a passage: for each Greek or Hebrew phrase, what it means and how it can be rendered (translation and lexical issues, not doctrinal commentary). Their key-term articles (Translation Words) are in the dictionary tool.

Inputs: ref (required), max_chars, include_intros.

wordA
Read-onlyIdempotent

Word study for a Strong's number (G26, H7225, H7225G) or lemma (agape, λόγος, reshit): lexicon entries (STEPBible brief lexicons, LSJ, Abbott-Smith, Dodson, Strong's, BDB glosses), UBS semantic senses with Louw-Nida domains and the other words in the same semantic field, occurrence count, distribution by book, renderings, grammatical forms, and references.

Inputs: key (required), max_refs.

xrefsB
Read-onlyIdempotent

Cross-references for one verse from OpenBible.info, ranked by community votes.

Inputs: ref (required), limit, min_votes.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 14 tools

    Disambiguation4/5

    Most tools target clearly distinct resources: passage (text), word (Strong's/lemma study), commentary, church_fathers, translation_notes, xrefs, dictionary, and search each have a distinct corpus or action. There is mild overlap between word and dictionary (both return lexicon entries for a Strong's number/lemma) and between search and dictionary (dictionary falls back to full-text search), plus four tools that all answer 'what does X say about this passage' — differentiated only by corpus, which the descriptions do clarify.

    Naming Consistency4/5

    Names follow a consistent resource-oriented convention (passage, word, search, commentary, dictionary, xrefs, sources, schema), with the *_modules suffix used predictably for commentary_modules and dictionary_modules. Minor deviations are check_quote (verb_noun) and the sql/schema escape-hatch pair, but everything remains readable and predictable.

    Tool Count5/5

    14 tools sits squarely in the well-scoped 3-15 range for a domain as broad as Bible study. Each tool covers a distinct corpus or operation, and the schema/sql pair serves as a deliberate escape hatch rather than filler.

    Completeness4/5

    Coverage is strong: text, original language, interlinear morphology, word studies, full-text search, three commentary corpora, dictionaries, cross-references, translation notes, provenance (sources), and a SQL fallback for anything uncovered. Minor gaps: passage appears to expose only the BSB translation even though sources tracks multiple versions, and grammatical/morphology search is only reachable through raw sql rather than a first-class tool.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Provides comprehensive Biblical research tools including scripture lookup, interlinear Greek/Hebrew data, and Strong's concordance within a Protestant theological framework. It enables AI applications to perform full-text biblical searches, topical studies, and cross-referencing using authoritative theological data.
      4
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables Claude.ai to access and retrieve Bible verses, passages, chapters, and lists of books or translations from public domain versions like KJV, using the free bible-api.com.
      MIT