# Besorah — the Bible in Hebrew, Greek, Aramaic and English (remote · besorah.bible)

The Bible in Hebrew, Greek and Aramaic: grammar search, Strong's, Septuagint, Targum. Free, no key.

- Trust score: 76/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `besorah.bible`: 76/100 (this document), [markdown](https://verifymcp.io/servers/bible-besorah-besorah/besorah.md), [page](https://verifymcp.io/servers/bible-besorah-besorah/besorah)

## Channel facts

- Endpoint: `https://besorah.bible/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - 58% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 5618 tokens (~193/item across 29 items; 24 tools + 5 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 24 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 26 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Besorah — the Bible in Hebrew, Greek, Aramaic and English MCP server?

Besorah — the Bible in Hebrew, Greek, Aramaic and English is a hosted endpoint at https://besorah.bible/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http bible-besorah-besorah 'https://besorah.bible/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "bible-besorah-besorah": {
      "url": "https://besorah.bible/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "bible-besorah-besorah": {
      "type": "http",
      "url": "https://besorah.bible/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.bible-besorah-besorah]
url = "https://besorah.bible/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "bible-besorah-besorah": {
      "type": "remote",
      "url": "https://besorah.bible/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add bible-besorah-besorah --url 'https://besorah.bible/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  bible-besorah-besorah:
    url: "https://besorah.bible/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "bible-besorah-besorah": {
      "Transport": "http",
      "Url": "https://besorah.bible/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add bible-besorah-besorah -t streamable-http -u 'https://besorah.bible/mcp'
```

### Other

```json
{
  "mcpServers": {
    "bible-besorah-besorah": {
      "type": "http",
      "url": "https://besorah.bible/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 76, +1)

- [security] Tool “compare_books” rewrote its description, which is the text the model reads
- [security] Tool “compare_witnesses” rewrote its description, which is the text the model reads
- [security] Tool “get_parashah” rewrote its description, which is the text the model reads
- [security] Tool “get_quotations” rewrote its description, which is the text the model reads
- [security] Tool “get_septuagint_connections” rewrote its description, which is the text the model reads
- [security] Tool “get_targum_connections” rewrote its description, which is the text the model reads
- [security] Tool “get_verse_study” rewrote its description, which is the text the model reads
- [security] Tool “get_word_occurrences” rewrote its description, which is the text the model reads
- [security] Tool “query_words” rewrote its description, which is the text the model reads
- [cosmetic] “get_collocations” reworded the description of “corpus”
- [cosmetic] “search_text” reworded the description of “testament”
- [cosmetic] Tool “get_quotations” changed its title: New Testament quotations → New Covenant (New Testament) quotations
- [cosmetic] Tool “get_septuagint_connections” changed its title: Hebrew, Greek and New Testament links → Hebrew, Greek and New Covenant links

### 2026-11-18 (score 75, +1)

- [functional] New tool “get_septuagint_connections”

### 2026-11-16 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 72, 0)

- [security] Tool “compare_books” rewrote its description, which is the text the model reads
- [security] Tool “compare_witnesses” rewrote its description, which is the text the model reads
- [security] Tool “get_book_connections” rewrote its description, which is the text the model reads
- [security] Tool “get_collocations” rewrote its description, which is the text the model reads
- [security] Tool “get_context” rewrote its description, which is the text the model reads
- [security] Tool “get_cross_references” rewrote its description, which is the text the model reads
- [security] Tool “get_guide” rewrote its description, which is the text the model reads
- [security] Tool “get_parashah” rewrote its description, which is the text the model reads
- [security] Tool “get_passage” rewrote its description, which is the text the model reads
- [security] Tool “get_quotations” rewrote its description, which is the text the model reads
- [security] Tool “get_related_passages” rewrote its description, which is the text the model reads
- [security] Tool “get_targum_connections” rewrote its description, which is the text the model reads
- [security] Tool “get_verse_study” rewrote its description, which is the text the model reads
- [security] Tool “get_vocabulary” rewrote its description, which is the text the model reads
- [security] Tool “get_word” rewrote its description, which is the text the model reads
- [security] Tool “get_word_occurrences” rewrote its description, which is the text the model reads
- [security] Tool “list_books” rewrote its description, which is the text the model reads
- [security] Tool “list_questions” rewrote its description, which is the text the model reads
- [security] Tool “list_songs” rewrote its description, which is the text the model reads
- [security] Tool “query_words” rewrote its description, which is the text the model reads
- [security] Tool “search_text” rewrote its description, which is the text the model reads
- [security] Tool “search_words” rewrote its description, which is the text the model reads
- [security] Tool “trace_theme” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 161 → 186
- [functional] Schema quality: good → excellent
- [cosmetic] “compare_books” reworded the description of “limit”
- [cosmetic] “get_book_connections” reworded the description of “limit”
- [cosmetic] “get_collocations” reworded the description of “limit”
- [cosmetic] “get_cross_references” reworded the description of “limit”
- [cosmetic] “get_quotations” reworded the description of “limit”
- [cosmetic] “get_vocabulary” reworded the description of “limit”
- [cosmetic] “get_word_occurrences” reworded the description of “limit”
- [cosmetic] “query_words” reworded the description of “limit”
- [cosmetic] “search_text” reworded the description of “limit”
- [cosmetic] “search_words” reworded the description of “limit”
- [cosmetic] “trace_theme” reworded the description of “limit”

### 2026-11-12 (score 72, +2)

- [security] Tool “compare_books” rewrote its description, which is the text the model reads
- [security] Tool “compare_witnesses” rewrote its description, which is the text the model reads
- [security] Tool “get_book_connections” rewrote its description, which is the text the model reads
- [security] Tool “get_collocations” rewrote its description, which is the text the model reads
- [security] Tool “get_context” rewrote its description, which is the text the model reads
- [security] Tool “get_cross_references” rewrote its description, which is the text the model reads
- [security] Tool “get_guide” rewrote its description, which is the text the model reads
- [security] Tool “get_parashah” rewrote its description, which is the text the model reads
- [security] Tool “get_passage” rewrote its description, which is the text the model reads
- [security] Tool “get_quotations” rewrote its description, which is the text the model reads
- [security] Tool “get_related_passages” rewrote its description, which is the text the model reads
- [security] Tool “get_targum_connections” rewrote its description, which is the text the model reads
- [security] Tool “get_verse_study” rewrote its description, which is the text the model reads
- [security] Tool “get_vocabulary” rewrote its description, which is the text the model reads
- [security] Tool “get_word” rewrote its description, which is the text the model reads
- [security] Tool “get_word_occurrences” rewrote its description, which is the text the model reads
- [security] Tool “list_books” rewrote its description, which is the text the model reads
- [security] Tool “list_questions” rewrote its description, which is the text the model reads
- [security] Tool “list_songs” rewrote its description, which is the text the model reads
- [security] Tool “query_words” rewrote its description, which is the text the model reads
- [security] Tool “search_text” rewrote its description, which is the text the model reads
- [security] Tool “search_words” rewrote its description, which is the text the model reads
- [security] Tool “trace_theme” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 129 → 161
- [functional improvement] Tool coverage: 71% → 100%
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 2.1 → 2.2
- [cosmetic] “compare_books” reworded the description of “editionA”
- [cosmetic] “compare_books” reworded the description of “editionB”
- [cosmetic] “get_book_connections” reworded the description of “limit”
- [cosmetic] “get_collocations” reworded the description of “corpus”
- [cosmetic] “get_context” reworded the description of “edition”
- [cosmetic] “get_parashah” reworded the description of “date”
- [cosmetic] “get_parashah” reworded the description of “list”
- [cosmetic] “get_parashah” reworded the description of “name”
- [cosmetic] “get_passage” reworded the description of “edition”
- [cosmetic] “get_passage” reworded the description of “words”
- [cosmetic] “get_quotations” reworded the description of “offset”
- [cosmetic] “get_related_passages” reworded the description of “limit”
- [cosmetic] “get_verse_study” reworded the description of “edition”
- [cosmetic] “get_vocabulary” reworded the description of “book”
- [cosmetic] “get_vocabulary” reworded the description of “offset”
- [cosmetic] “get_vocabulary” reworded the description of “view”
- [cosmetic] “get_word_occurrences” reworded the description of “book”
- [cosmetic] “get_word_occurrences” reworded the description of “offset”
- [cosmetic] “get_word_occurrences” reworded the description of “strongs”
- [cosmetic] “list_questions” reworded the description of “contains”
- [cosmetic] “list_questions” reworded the description of “theme”
- [cosmetic] “list_songs” reworded the description of “kind”
- [cosmetic] “query_words” reworded the description of “book”
- [cosmetic] “query_words” reworded the description of “offset”
- [cosmetic] “search_text” reworded the description of “book”
- [cosmetic] “search_text” reworded the description of “edition”
- [cosmetic] “search_text” reworded the description of “language”
- [cosmetic] “search_text” reworded the description of “offset”
- [cosmetic] “search_text” reworded the description of “query”
- [cosmetic] “search_text” reworded the description of “testament”
- [cosmetic] “search_words” reworded the description of “query”
- [cosmetic] “trace_theme” reworded the description of “follow”

### 2026-11-11 (score 70)

First indexed and scored.

## MCP tools (24)

### `get_passage` (~278 tokens)

Read a passage

Returns a verse, range or chapter in its original language (Hebrew, Greek or Aramaic) with its English and a link; a range is capped at 80 verses. edition (septuagint, onkelos, pseudo-jonathan, jonathan, hebrew-nt, hebrew, greek) chooses the text. words=true adds, for each verse whose words line up with the Strong's tagging, every word's Strong's number, lemma, meaning and grammatical parsing. Use when the user asks to read or quote a verse, range or chapter.

Input parameters:

- `edition` (string): which text, e.g. septuagint, onkelos, pseudo-jonathan, jonathan, hebrew-nt, hebrew or greek
- `format` (string): optional: json (default) or markdown (compact, readable)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `reference` (string, required): e.g. 'John 3:16', 'Psalm 23', 'Genesis 1:1-3', '1 Corinthians 13:4-7'
- `words` (boolean): true adds each word's Strong's number, lemma, meaning and parsing

### `get_verse_study` (~266 tokens)

Study a verse

Returns one verse, or a range of up to 5, in full: the original and English text; word-by-word Strong's number, lemma and parsing where the words line up with the tagging; and the verse's cross-references, quotations between books, curated parallels, similar wording, questions it asks or answers, songs, scribal marks, Ketiv/Qere, Targum connections and, where the Hebrew says the LORD’s word came to a prophet, that recipient and the other places it came to them. Use when the user wants a thorough look at one verse, or up to five.

Input parameters:

- `edition` (string): which text, e.g. septuagint, onkelos, pseudo-jonathan, jonathan, hebrew-nt, hebrew or greek
- `format` (string): optional: json (default) or markdown (compact, readable)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `reference` (string, required): e.g. 'John 3:16', 'Psalm 23', 'Genesis 1:1-3', '1 Corinthians 13:4-7'

### `search_text` (~369 tokens)

Search the text

Returns the verses that match a search of the text, in Bible order, each with its reference, link and text; 10 per page by default (limit 1-25, and nextOffset continues). English by default; language=hebrew|greek|aramaic searches the original with vowel points and accents ignored. Every word must be in the verse; \"quoted phrase\" matches exact order; a trailing * matches word endings (lov*); English words are matched as written, without stemming. Narrow with book, testament (tanakh|new testament|apocrypha) or edition. Use when the user searches for words or phrases in the text itself.

Input parameters:

- `book` (string): restrict to one book, e.g. Isaiah
- `edition` (string): which text, e.g. septuagint, onkelos, pseudo-jonathan, jonathan, hebrew-nt, hebrew or greek
- `format` (string): optional: json (default) or markdown (compact, readable)
- `language` (string): which text is searched: english, hebrew, greek or aramaic
- `limit` (number): how many results to return (1-25, default 10)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `offset` (number): how many results to skip; the previous answer's nextOffset is where its page ended
- `query` (string, required): the words or "quoted phrase" to find; a trailing * matches word endings (lov*)
- `testament` (string): tanakh, new covenant (also accepted: new testament, nt) or apocrypha

### `search_words` (~201 tokens)

Find a Hebrew or Greek word

Finds Hebrew and Greek words (Strong's entries) from an English word, a transliteration ('shalom', 'agape') or the original word. Returns the best matches first (10 by default, up to 25), each with its Strong's id, lemma, definition, occurrence count and link; 'more' says how many further matches exist. Use when the user asks which Hebrew or Greek word lies behind an English word or transliteration.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return (1-25, default 10)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `query` (string, required): an English word, a transliteration (shalom, agape) or the Hebrew or Greek word itself

### `get_word` (~180 tokens)

Look up a word

Returns one Strong's entry (Hebrew H… or Greek G…): lemma, transliteration, definition, KJV renderings, occurrence count and verses per book. For Hebrew it adds the Brown–Driver–Briggs entry and, for a name, how it is built from its parts; it also gives the Septuagint renderings of a Hebrew word, or the Hebrew words a Greek word renders. Use when the user asks what a Hebrew or Greek word means, given its Strong's number.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `strongs` (string, required): e.g. H430 or G26

### `get_word_occurrences` (~243 tokens)

Every verse a word is in

Lists every verse that contains a Strong's number (Hebrew Tanakh, Greek New Covenant (New Testament) and Septuagint), in Bible order with the verse text, plus the count per book. Covers every form of the word; optionally limited to one book. 10 verses per page by default (limit 1-25, and nextOffset continues). Use when the user asks where a particular Hebrew or Greek word occurs.

Input parameters:

- `book` (string): restrict to one book code or name, e.g. PSA or Psalms
- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return (1-25, default 10)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `offset` (number): how many results to skip; the previous answer's nextOffset is where its page ended
- `strongs` (string, required): a Strong's number such as H2617 (Hebrew) or G26 (Greek)

### `get_related_passages` (~161 tokens)

Related passages

Returns the verses connected to one verse, grouped by kind: voted cross-references, quotations in either direction between books, curated parallel passages, and similar wording. Use when the user asks what passages are related to one verse.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `reference` (string, required): e.g. 'John 3:16', 'Psalm 23', 'Genesis 1:1-3', '1 Corinthians 13:4-7'

### `get_cross_references` (~180 tokens)

Cross-references

Returns the voted cross-references (OpenBible.info) of one verse, each with its reference and link; the first few also carry their English text. 12 by default (limit 1-30). Use when the user asks for the cross-references of one verse.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return (1-30, default 12)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `reference` (string, required): e.g. 'John 3:16', 'Psalm 23', 'Genesis 1:1-3', '1 Corinthians 13:4-7'

### `get_book_connections` (~179 tokens)

Connections between books

Returns the chapters a book, or one chapter, is most connected to elsewhere in the Bible: chapter pairs joined by at least two verse-level cross-references (OpenBible.info), most-linked first, each with its link count and a link. 15 by default (limit 1-40). Use when the user asks which chapters a book or chapter is most connected to.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return (1-40, default 15)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `reference` (string, required): a book ('Isaiah') or a chapter ('Psalm 22')

### `list_books` (~111 tokens)

List the books

Returns every book with its code, chapter count, the editions it exists in and its URL, and the list of editions. The whole list comes back in one piece. Use when the user asks what books, editions or book codes are available.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)

### `list_songs` (~188 tokens)

Songs and prayers in Scripture

Returns the songs and prayers inside Scripture (the Song of the Sea, Hannah's prayer, the Magnificat…), each with its name, Hebrew title, kind (victory, prophetic, thanksgiving, boast, prayer, work song, blessing, lament or hymn), passage reference and link. kind narrows the list; otherwise the whole list comes back in one piece. Use when the user asks which songs and prayers appear inside Scripture, such as the Song of the Sea or the Magnificat.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `kind` (string): kind of song or prayer, e.g. victory, lament, prayer, blessing, hymn, thanksgiving
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)

### `list_questions` (~208 tokens)

Questions and their answers

Returns pairs of passages in which a question asked in one place is answered in another (e.g. 'what is man?' in Job and Psalm 8). Each pair has its theme, the asking and answering passages, and a note. theme (god, man, suffering, sin, death, time, wisdom, worship, messiah) or contains narrows the list; unfiltered, every pair comes back in one large piece. Use when the user asks about a question in one passage that another passage answers.

Input parameters:

- `contains` (string): only questions whose text contains this word
- `format` (string): optional: json (default) or markdown (compact, readable)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `theme` (string): theme id: god, man, suffering, sin, death, time, wisdom, worship or messiah

### `get_targum_connections` (~177 tokens)

Targum connections

Returns the curated list of places where the Targumim (the Aramaic translations of the Torah and Isaiah) and the New Covenant (New Testament) share an idea, phrase or contrast. Each entry has a title, whether it is a shared idea or a contrast, the Targum passages, the New Covenant passages, and a note saying what is and is not claimed. The whole list comes back in one piece; it takes no filter. Use when the user asks where Targum wording and the New Covenant (New Testament) overlap.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)

### `get_septuagint_connections` (~299 tokens)

Hebrew, Greek and New Covenant links

Returns the curated places where a Hebrew term or idea is carried through the Septuagint into the New Covenant (New Testament). Each entry has a title, its kind (a Greek word traced back to its Hebrew term, an idea the Greek says more openly than the Masoretic Hebrew, or a passage from a book found only in Greek), the Hebrew, Greek (Septuagint numbering) and New Covenant passages, Strong's pairs for word entries, and a note saying what is and is not claimed. kind (idea, word, only), topic (lord, messiah, covenant, life) or contains narrows the list; unfiltered, every entry comes back in one large piece. Use when the user asks how a New Covenant (New Testament) Greek word or idea traces back through the Septuagint to the Hebrew canon.

Input parameters:

- `contains` (string): only entries whose title or note contains this text
- `format` (string): optional: json (default) or markdown (compact, readable)
- `kind` (string): idea (the Greek says it more openly), word (a Greek word traced back) or only (a book found only in Greek)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `topic` (string): lord, messiah, covenant or life

### `get_parashah` (~225 tokens)

Weekly Torah portion

Returns a weekly Torah portion: its name, Hebrew name, meaning and Shabbat date, with its Torah, Haftarah and Besorah (New Covenant) readings and links, on the Diaspora calendar. Give a name ('Toledot'), a date (YYYY-MM-DD) for the portion read on the Shabbat on or after it, or list=true for every portion; with none, this week's. Use when the user asks about a weekly Torah portion, its Haftarah or its New Covenant (New Testament) reading.

Input parameters:

- `date` (string): a date as YYYY-MM-DD; gives the portion read on the Shabbat on or after it
- `format` (string): optional: json (default) or markdown (compact, readable)
- `list` (boolean): true returns every portion
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `name` (string): portion name, e.g. Toledot

### `get_guide` (~121 tokens)

Guide to the texts and tools

Returns a plain-text guide to Besorah's texts and conventions: the editions, the Hebrew-based verse numbering, Strong's ids (H… Hebrew, G… Greek), book codes, and what each study tool returns. Use when the user asks how the texts, numbering and ids work.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)

### `query_words` (~386 tokens)

Find words by grammar

Finds every word by grammar and/or Strong's number, within a book or testament — e.g. all Qal imperatives of H1285 in the Prophets, every aorist passive participle in Paul, every Hiphil verb in Isaiah. grammar takes the words of the parsing (Qal, Hiphil, imperative, participle, feminine, plural, aorist, passive, genitive, 3rd…); all must be on the same word. Hebrew by default for H ids and Tanakh books, Greek for G ids and the New Covenant (New Testament); edition=septuagint for the Septuagint. Returns the matching words with their verses and a count per book, 10 per page by default (limit 1-25, and nextOffset continues). Use when the user asks for words by grammatical form, such as every Qal imperative or aorist passive participle.

Input parameters:

- `book` (string): restrict to one book, e.g. Isaiah
- `edition` (string): hebrew | greek | septuagint
- `format` (string): optional: json (default) or markdown (compact, readable)
- `grammar` (string): e.g. 'Qal imperative', 'aorist passive participle', 'feminine plural'
- `limit` (number): how many results to return (1-25, default 10)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `offset` (number): how many results to skip; the previous answer's nextOffset is where its page ended
- `strongs` (string): e.g. H1285 (optional)
- `testament` (string): tanakh | new testament | apocrypha

### `get_collocations` (~252 tokens)

Words that keep company

Returns the words that keep company with a Hebrew or Greek word: those that appear in the same verse more often than chance predicts (log-likelihood), strongest first, 15 by default (limit 1-25). Pass strongs (H430) or a word ('shepherd'). Pass with=<Strong's id> to read the verses where two words meet. corpus: he, nt or lxx. Use when the user asks which words commonly appear alongside a given Hebrew or Greek word.

Input parameters:

- `corpus` (string): he (Hebrew Bible), nt (Greek New Covenant, also called the New Testament) or lxx (Septuagint)
- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return (1-25, default 15)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `strongs` (string, required): H430, or an English/transliterated word
- `with` (string): a second Strong's id, to see the verses with both

### `get_vocabulary` (~247 tokens)

A book's vocabulary

Returns a book's vocabulary. view=summary (default) gives its size, distinct words, hapax legomena (words used once in the whole text), words found only in that book, and its most frequent and most characteristic words; view=hapax, unique or words lists those words (25 per page by default, limit 1-100, and nextOffset continues). Use when the user asks about one book's vocabulary, rare words or words unique to it.

Input parameters:

- `book` (string, required): the book, e.g. Ruth
- `edition` (string): hebrew | greek | septuagint
- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return (1-100, default 25)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `offset` (number): how many results to skip; the previous answer's nextOffset is where its page ended
- `view` (string): summary, hapax, unique or words

### `compare_books` (~253 tokens)

Compare two books' vocabulary

Compares two books' vocabularies: the word counts of each, how many words they share, the rare words they share (most of whose uses are in these two books), and the words only one uses, 15 of each by default (limit 1-40). Same language only: two Hebrew books, two Greek ones, or a Septuagint book (editionA: septuagint) against a New Covenant (New Testament) book. Use when the user asks how the vocabularies of two books compare.

Input parameters:

- `a` (string, required): e.g. Isaiah
- `b` (string, required): e.g. Matthew
- `editionA` (string): edition of the first book, e.g. septuagint
- `editionB` (string): edition of the second book, e.g. hebrew-nt
- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return (1-40, default 15)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)

### `get_context` (~242 tokens)

A verse in its setting

Returns a verse in its setting in one call: the verses before and after (2 each by default, 0-8), the verse itself, or up to 5, word by word, and its cross-references, quotations and parallels. Combines several lookups into one answer. Use when the user asks what surrounds a verse, with its neighbouring verses and connections.

Input parameters:

- `after` (number): verses after, 0-8, default 2
- `before` (number): verses before, 0-8, default 2
- `edition` (string): which text, e.g. septuagint, onkelos, pseudo-jonathan, jonathan, hebrew-nt, hebrew or greek
- `format` (string): optional: json (default) or markdown (compact, readable)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `reference` (string, required): e.g. 'John 3:16', 'Psalm 23', 'Genesis 1:1-3'

### `trace_theme` (~264 tokens)

Trace a theme

Follows a passage's connections outward — voted cross-references plus quotations and parallels between books — one to three steps (depth, default 2), and returns the most strongly connected verses (20 by default, limit 1-40) with their text, hops from the start, strength (it grows with the number of short paths that reach the verse) and how each was reached. Example: the connections of Passover outward from Exodus 12. Use when the user asks to follow a theme or passage outward through the Bible.

Input parameters:

- `breadth` (number): links followed per verse, 2-10, default 5
- `depth` (number): 1-3 steps, default 2
- `follow` (string): both, xref (cross-references only) or quotes (quotations and parallels only)
- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return (1-40, default 20)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `reference` (string, required): a verse, short range or chapter

### `compare_witnesses` (~193 tokens)

Compare the texts of a verse

Returns one verse across the texts side by side: Hebrew, the Septuagint (matched by the app's verse tables, even where numbered differently), the Targumim, and the Greek and Hebrew New Covenant (New Testament), with the quotations that join them and the Greek words a New Covenant quotation and the Septuagint do and do not share. Use when the user asks how one verse reads in the Hebrew, Septuagint, Targum and New Covenant (New Testament).

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `reference` (string, required): e.g. 'John 3:16', 'Psalm 23', 'Genesis 1:1-3'

### `get_quotations` (~245 tokens)

New Covenant (New Testament) quotations

Returns where the New Covenant (New Testament) quotes the Tanakh, in either direction: give a New Covenant book, chapter or verse for the Tanakh (Old Testament) passages it quotes, or a Tanakh one for the New Covenant passages that quote it. Each result carries both English texts and a link; 15 per page by default (limit 1-40, and nextOffset continues). Use when the user asks where the New Covenant (New Testament) quotes the Tanakh (Old Testament), or the reverse.

Input parameters:

- `format` (string): optional: json (default) or markdown (compact, readable)
- `limit` (number): how many results to return (1-40, default 15)
- `max_chars` (number): optional: cap the answer at about this many characters (lists are shortened and marked truncated; use offset/nextOffset to get the rest)
- `offset` (number): how many results to skip; the previous answer's nextOffset is where its page ended
- `reference` (string, required): e.g. 'Matthew', 'Hebrews 1', 'Psalm 110:1', 'Isaiah 53'

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/bible-besorah-besorah/besorah#diagnostics

## Score history

- 2026-11-21: 76
- 2026-11-20: 76
- 2026-11-19: 75
- 2026-11-18: 75
- 2026-11-17: 74
- 2026-11-16: 74
- 2026-11-15: 73
- 2026-11-14: 73
- 2026-11-13: 72
- 2026-11-12: 72
- 2026-11-11: 70

## Common questions

### What is the Besorah — the Bible in Hebrew, Greek, Aramaic and English MCP server?

Besorah — the Bible in Hebrew, Greek, Aramaic and English is an MCP server listed in the public MCP registry as bible.besorah/besorah. The Bible in Hebrew, Greek and Aramaic: grammar search, Strong's, Septuagint, Targum. Free, no key. This page covers its hosted endpoint (https://besorah.bible/mcp).

### Is the Besorah — the Bible in Hebrew, Greek, Aramaic and English MCP server safe to use?

Besorah — the Bible in Hebrew, Greek, Aramaic and English scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Besorah — the Bible in Hebrew, Greek, Aramaic and English MCP server expose?

Besorah — the Bible in Hebrew, Greek, Aramaic and English exposes 24 tools: get_passage, get_verse_study, search_text, search_words, get_word, and 19 more. Their descriptions and schemas cost roughly 5,468 tokens of context every time the server is loaded.

### Does the Besorah — the Bible in Hebrew, Greek, Aramaic and English MCP server require authentication?

No. We connected to Besorah — the Bible in Hebrew, Greek, Aramaic and English without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Besorah — the Bible in Hebrew, Greek, Aramaic and English MCP server still maintained?

Besorah — the Bible in Hebrew, Greek, Aramaic and English is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Besorah — the Bible in Hebrew, Greek, Aramaic and English MCP server?

VerifyMCP ran 13 checks on Besorah — the Bible in Hebrew, Greek, Aramaic and English, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://besorah.bible/mcp
- Website: https://besorah.bible/about/ai/
- Changelog RSS feed: https://verifymcp.io/servers/bible-besorah-besorah/besorah.xml
- Changelog JSON feed: https://verifymcp.io/servers/bible-besorah-besorah/besorah/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/bible-besorah-besorah/besorah.json
- HTML version of this page: https://verifymcp.io/servers/bible-besorah-besorah/besorah
