Command documentation

sources

Inventory source provenance, capabilities, and coverage.

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_sources. The MCP Server Card is /.well-known/mcp/server-card.json.

Parameters

Name	Required	Description
`limit`	no	Maximum source inventory rows per source table or capability group. The default is higher because inventory views are diagnostic, but still capped to avoid full dumps. Default 100, max 500.
`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 sources it expands source capability, coverage, and conflict context.
`kind`	no	Source inventory family, such as base_text, ancient_translation, manuscript, resource, lexicon, apparatus, or dataset. It narrows source/capability rows.
`language`	no	Language filter for source inventory rows, such as heb, grc, lat, syr, or eng. Use it to narrow sources, not to translate results.
`status`	no	Source/status filter for inventory rows. Use it to focus on loaded, available, pending, or diagnostic source groups.
`sources`	no	Source-code filters for inventory rows, such as OSHB, LXX, DSS, Vulgate, Peshitta, or a loaded source code.

Examples

HTTP

curl -s 'https://bible.grod.es/api/sources?depth=1&kind=ancient_translation&language=grc&sources=LXX'

MCP

{
  "arguments": {
    "depth": 1,
    "kind": "ancient_translation",
    "language": "grc",
    "sources": [
      "LXX"
    ]
  },
  "name": "bible_sources"
}

CLI

bible sources --depth 1 --kind ancient_translation --language grc --sources LXX

Caveats for this command

Inventory and audit output describes loaded local data and known gaps. It is not a claim of exhaustive global coverage.
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.