AI-SDLC Prompts MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_promptsA | Lista los prompts de la biblioteca AI-SDLC Pro, con filtro opcional por sección (00-17), riesgo esperado (low/medium/high/variable), autonomía permitida (A0-A3) y texto libre (busca en título y descripción). |
| get_promptA | Devuelve el detalle completo de un prompt por id: título, descripción, texto crudo del prompt (con placeholders [ASI] sin resolver), fórmulas de uso, contrato editorial y siguiente(s) prompt(s) recomendado(s). |
| resolve_promptA | Sustituye los placeholders del prompt (y opcionalmente del preámbulo del framework) con las variables provistas -- misma sustitución que hace el sitio. Las claves de 'variables' son los campos canónicos (repositorio, referencia, rama_actual, rama_destino, ambiente, componentes, modulo, stack, tipo_proyecto, metodologia, agentes, autonomia, entrada, objetivo, responsable, workspace, compliance, documentos, profundidad, adicionales), no los alias en mayúsculas del texto. Devuelve el texto resuelto y los placeholders obligatorios/opcionales que quedaron sin resolver. |
| get_frameworkA | Devuelve el preámbulo obligatorio del framework AI-SDLC (principio operativo que se antepone a cualquier prompt de la biblioteca). |
| recommend_nextB | Devuelve el/los prompt(s) que el contrato editorial recomienda usar después de uno dado. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct role: listing with filters, fetching full detail, retrieving the framework preamble, following editorial recommendations, and resolving placeholders. The potentially confusable pair (get_prompt vs resolve_prompt) is explicitly separated by 'texto crudo con placeholders sin resolver' versus 'sustituye los placeholders'.
Four of five names follow a clean verb_noun pattern (list_prompts, get_prompt, get_framework, resolve_prompt) in consistent snake_case. recommend_next is verb+adverb without an object noun, a minor deviation from an otherwise predictable scheme.
Five tools is a tight, well-scoped surface for a read-only prompt library: browse, read, resolve, navigate, and load the framework preamble. No tool appears redundant and none feels missing for the stated purpose.
Core lifecycle for consuming the library is covered end-to-end: discover via filters, inspect, resolve placeholders, and jump to the next recommended prompt. Minor gaps remain, such as no way to enumerate sections or the canonical variable/placeholder schema without first calling resolve_prompt on a specific prompt.