Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
juba_searchA

Search JUBA for court decision summaries (sumarios) by keyword.

Args:
    query: Search terms (e.g., "consumidor vicio", "prescripción laboral").
    materia: Legal subject area. Options: civil, laboral, penal, contencioso,
             inconstitucionalidad, conflicto, enjuiciamiento, todos.
             Default: civil.
    limit: Maximum results to return (up to 15 per page).

Returns:
    JSON with total count, tab counts (text vs voces vs full text matches),
    and result list. Each result has: id, voces (legal topics), texto (summary text),
    normas (cited statutes), and fallo metadata (tribunal, fecha, caratula, magistrados).
juba_advanced_searchA

Advanced search on JUBA with field-specific filtering.

Searches across specific fields like summary text, voces (legal topics),
case caption (caratula), full ruling text, or cited norms.

Args:
    query: Search terms. Supports etiquetas like "Caratula:Garcia" or "TipoFallo:S".
    fields: Which fields to search in. Default: ["texto_sumario"].
            Options: materia, voces, nro_causa, caratula, texto_sumario,
            juez_voto, codigo_norma, nro_norma, anio_norma,
            texto_completo, tribunal_emisor.
    tipo_fallo: Filter by ruling type. S=Definitiva, I=Interlocutoria, P=Plenario.
    fecha_desde: Start date filter (DD/MM/YYYY).
    fecha_hasta: End date filter (DD/MM/YYYY).

Returns:
    JSON with total count and result list with same structure as juba_search.
juba_get_falloA

Retrieve the full text of a court ruling by its numeric ID.

Use id_fallo values from search results to get the complete ruling text,
including the full judicial reasoning, not just the summary.

Args:
    id_fallo: Numeric ruling ID from search results (e.g., 191298).

Returns:
    JSON with metadata (tribunal, caratula, fecha) and full ruling text.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.6/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: juba_advanced_search offers field-specific filtering, juba_get_fallo retrieves full ruling text by ID, and juba_search provides basic keyword search for summaries. There is no overlap in functionality, making tool selection unambiguous for an agent.

Naming Consistency5/5

All tool names follow a consistent 'juba_' prefix with descriptive snake_case suffixes (advanced_search, get_fallo, search). This predictable pattern enhances readability and coherence across the tool set.

Tool Count5/5

With 3 tools, the server is well-scoped for its domain of accessing court rulings. Each tool earns its place by covering distinct aspects: basic search, advanced search, and full-text retrieval, avoiding bloat or thin coverage.

Completeness5/5

The tool surface provides complete coverage for the domain of court ruling access: search (basic and advanced) and retrieval of full texts. There are no obvious gaps, as agents can find rulings and access their details without dead ends.

Maintenance

ActivityInactive
ResponsivenessNo issues