Command documentation
study
Synthesize a reference, word, entity, topic, or source object through the main bounded aggregator.
Purpose
This command is available over HTTP, MCP and the local CLI. HTTP responses use the compact public response shape with summaries, warnings and bounded tables.
MCP connection
Use endpoint https://bible.grod.es/mcp with tool bible_study. The MCP Server Card is /.well-known/mcp/server-card.json.
Parameters
| Name | Required | Description |
|---|---|---|
target | yes | Object to synthesize: Bible reference, Strong key, entity, topic, source, resource, or exact object ID. Target grammar: natural Bible reference, or prefix:value. Examples: Deut 32:8, John 1, ref:Deut 32:8, strong:H7225, entity:Paul, source:LXX, variant:<id>, resource:<id>. |
limit | no | Maximum items per synthesized section after the target payload is resolved. It is not an unbounded SQL join and not a single global top-N; each section keeps the most useful bounded rows for that lens. Effective caps are adjusted by numeric depth: depth 0 stays terse, depth 1 is the default useful context, and deeper requests can use up to the command maximum. Default 5, max 20. |
depth | no | Expansion depth from 0 to 10. 0 returns direct facts for the target; 1 is the default useful context; higher values include more related context and are clamped by the server --max-depth instead of failing. For study it also controls the effective per-section synthesis cap: direct facts stay terse, default context is broader, and deeper requests include more evidence-backed context. |
include_semantic | no | Include precomputed semantic-neighbor discovery where available. It is useful for exploration, but semantic similarity is not primary textual evidence. |
min_confidence_score | no | Minimum confidence threshold from 0 to 1. It filters numeric confidence_score values, or documented label-derived scores high=1, medium=0.6, low=0.3; rows without numeric confidence are not removed, and basis-only values such as source_attested or algorithmic are not treated as confidence scores. |
Required option sets: [["target"]]
Examples
HTTP
curl -s 'https://bible.grod.es/api/study?depth=2&include_semantic=true&min_confidence_score=0.6&target=Deut+32%3A8'MCP
{
"arguments": {
"depth": 2,
"include_semantic": true,
"min_confidence_score": 0.6,
"target": "Deut 32:8"
},
"name": "bible_study"
}CLI
bible study --depth 2 --include-semantic --min-confidence-score 0.6 Deut 32:8Caveats for this command
- Semantic options use precomputed local vectors when available. They are discovery aids, not primary textual evidence.
- DSS material is fragmentary.
- LXX GreekResources data is lemma-level and not a full critical apparatus.
- The runtime does not call LLM or embedding APIs.