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": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
datos_search_datasetsB

Busca datasets publicados por el INE en datos.gob.cl. Retorna título, nombre, número de recursos.

datos_get_datasetA

Metadata completa de un dataset del INE (recursos, formato, URL). Usa datos_search_datasets primero para encontrar el ID.

datos_query_resourceA

Consulta filas de un recurso tabular del INE vía CKAN datastore. Requiere resource_id (obtenible via datos_get_dataset).

inestat_list_dataflowsA

Lista todos los dataflows (datasets) disponibles en INE.Stat, con id y nombre. Soporta filtro por keyword.

inestat_get_structureA

Devuelve la estructura (dimensiones, codelists) de un dataflow específico. Útil para saber qué filtros aplicar antes de consultar datos.

inestat_get_dataB

Consulta observaciones de un dataflow de INE.Stat. Retorna datos en formato tabular.

simel_list_dataflowsB

Lista indicadores de mercado laboral (ENE, ESI) disponibles en SIMEL/INE.Stat.

simel_get_dataB

Consulta una serie laboral de SIMEL (ej: tasa de desocupación, ingreso medio). Los datos provienen de INE.Stat filtrados a datasets ENE_*/ESI_*.

codif_classify_activityA

Clasifica una o varias glosas de actividad económica en CAENES (1 o 2 dígitos). Input: array de strings. Output: códigos + probabilidades.

codif_classify_occupationA

Clasifica una o varias glosas de ocupación en CIUO-08.CL (1 o 2 dígitos). Input: array de strings. Output: códigos + probabilidades.

codif_get_training_dataB

Descarga una muestra de los sets train/test usados por el clasificador CAENES o CIUO.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 11 tools

Disambiguation5/5

Each tool has a distinct purpose with clear boundaries: codif_* tools handle classification and training data, datos_* tools manage dataset metadata and queries, inestat_* tools access statistical dataflows and structures, and simel_* tools focus on labor market indicators. There is no overlap in functionality, making tool selection unambiguous.

Naming Consistency5/5

Tool names follow a consistent verb_noun pattern with a clear prefix system: codif_, datos_, inestat_, and simel_ indicate the domain, followed by descriptive actions like classify, get, query, search, and list. This structured naming makes the tool set predictable and easy to navigate.

Tool Count5/5

With 11 tools, the server is well-scoped for its purpose of accessing INE Chile data across classification, datasets, statistics, and labor market indicators. Each tool serves a specific function, and the count is neither too sparse nor overwhelming for the domain coverage.

Completeness5/5

The tool set provides comprehensive coverage for interacting with INE Chile's data systems: classification (CAENES/CIUO), dataset metadata and queries (CKAN), statistical dataflows (INE.Stat), and labor market indicators (SIMEL). It supports full workflows from discovery to data retrieval, with no obvious gaps in the surface.