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
list_specsB

Lista specs legadas e features do pipeline SDD.

list_skillsB

Lista skills legadas e Agent Skills no formato SKILL.md.

get_skillC

Retorna o conteúdo de uma skill pelo nome do domínio.

validate_specC

Valida as seções obrigatórias de uma spec legada.

prepare_generation_contextC

Combina uma spec legada e uma skill em contexto para o agente.

steeringC

Lê ou inicializa a constituição em .kiro/steering/constitution.md.

spec-initC

Inicializa uma feature e cria o rascunho de requirements.md.

spec-requirementsC

Lê ou salva requirements.md. Salvar novamente remove aprovações downstream.

spec-designB

Lê ou salva design.md depois da aprovação dos requisitos.

spec-tasksC

Lê ou salva tasks.md depois da aprovação do design.

spec-approveC

Registra aprovação humana explícita para requisitos, design ou tarefas.

spec-implC

Prepara contexto TDD das tarefas aprovadas; o agente implementa no repositório.

spec-statusC

Mostra aprovações e progresso das tarefas de uma feature.

spec-feedbackC

Gera relatório de status ou análise de lacunas do workflow.

validate-designC

Valida as seções necessárias do design técnico.

validate-gapC

Compara aprovações e tarefas com um resumo fornecido da implementação.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

C2.8/5.0

Scored across 16 tools

Disambiguation4/5

Most tools target a clearly distinct stage or artifact (spec-init, spec-requirements, spec-design, spec-tasks, spec-approve, spec-impl). The main overlap is spec-status vs spec-feedback, both of which surface progress/status information, and the three validate_* tools differ only by target. Descriptions largely resolve these ambiguities.

Naming Consistency2/5

The set mixes two conventions: snake_case (list_specs, get_skill, validate_spec, prepare_generation_context) and kebab-case (spec-init, spec-requirements, validate-design, validate-gap), plus a bare noun 'steering'. While the spec-* family is internally consistent, the overall pattern is unpredictable.

Tool Count3/5

16 tools is borderline-heavy for a spec-driven-development server. Many serve a genuine lifecycle stage, but the validate_* trio and the status/feedback pair feel partially redundant, suggesting some tools could be consolidated.

Completeness4/5

The surface covers the full spec lifecycle: init, requirements, design, tasks, approval, implementation prep, status, feedback, plus skills/steering and validation. Minor gaps around editing/versioning of specs exist, but core CRUD-style workflows are covered without dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues