AI-SDLC Prompts

Name: AI-SDLC Prompts
Author: dleon55

by dleon55version 1.0.2i★ –iRuns on your computer

Registry nameio.github.dleon55/ai-sdlc-prompts

Install

Overview

Description from the maker (original English)

112 SDLC prompts (ES/EN) for AI coding agents, each with its operating contract.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiEarly↓ 736/wk · ★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Developer tools

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
The registry lists no key to fill in.

You need

npmNode.js installed (for the npx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "ai-sdlc-prompts": {
      "command": "npx",
      "args": [
        "-y",
        "ai-sdlc-prompts-mcp"
      ]
    }
  }
}

Run this in your terminal

claude mcp add ai-sdlc-prompts -- npx -y ai-sdlc-prompts-mcp

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "ai-sdlc-prompts": {
      "command": "npx",
      "args": [
        "-y",
        "ai-sdlc-prompts-mcp"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "ai-sdlc-prompts": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ai-sdlc-prompts-mcp"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account dleon55, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Developer toolsi

More stars than 0% of the other 5549 servers in this category
Published to the registry more recently than 73% of the other 5549 servers in this category
Basic checks equal to or better than 100% of the other 5549 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is AI-SDLC Prompts safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (1.0.2) reached the registry 7 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: GitHub, Desktop Commander, Cloudflare MCP

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

GitHub

GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.

by githubWidely used★ 34.2KUpdated 5 days ago

Computer or cloud

Install

Desktop Commander

MCP server for terminal commands, file operations, and process management

by wonderwhy-erWidely used↓ 709.6K/wk★ 10.2KUpdated 17 days ago

Runs on your computer

Install

Cloudflare MCP

Cloudflare MCP servers

by cloudflareWidely used★ 4.4KUpdated 14 months ago

Runs in the cloud✓ mcp.cloudflare.com

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

AI-SDLC Prompts — servidor MCP

Expone la biblioteca de prompts AI-SDLC Pro (112 prompts, ES/EN) a agentes de IA (Claude Code, Claude Desktop, Cursor, etc.) vía Model Context Protocol, transporte stdio.

Solo lectura: ningún tool escribe en el repositorio, en GitHub ni en ningún sistema externo. Todo el contenido se sirve desde data/prompts-full.json, generado por python build.py en la raíz del repo — este servidor nunca parsea Markdown por su cuenta.

Todo prompt que sale de aquí viaja con su contrato de operación: techo de autonomía, herramientas permitidas, criterios de detención y evidencia mínima. Es el mismo bloque que pega quien copia desde el sitio, y resolve_prompt lo anexa por defecto — ver Contrato de operación.

Instalación

Publicado en npm: ai-sdlc-prompts-mcp.

Licencia: el código de este servidor es MIT; los prompts que sirve son

CC BY 4.0 (uso comercial permitido, con atribución). Ver LICENSE.

Sin clonar el repositorio:

npx ai-sdlc-prompts-mcp

Desde el clon local:

cd mcp-server

npm install

Ejecutar

npm start

equivalente a: node index.js

El proceso escucha en stdin/stdout (protocolo MCP) — no expone HTTP ni requiere red. Se cierra con Ctrl+C o cuando el cliente cierra la conexión.

Configurar en Claude Code / Claude Desktop

Agrega esto a la configuración de servidores MCP del cliente (claude_desktop_config.json o el equivalente de Claude Code), ajustando la ruta absoluta al checkout local:

"mcpServers": { "ai-sdlc-prompts": { "command": "node", "args": ["/ruta/absoluta/a/ai-sdlc-prompts/mcp-server/index.js"] } } }

Con el paquete de npm, sin ruta absoluta ni clon:

"mcpServers": { "ai-sdlc-prompts": { "command": "npx", "args": ["-y", "ai-sdlc-prompts-mcp"] } } }

Contrato de operación

Cada uno de los 112 prompts declara en su contrato editorial hasta dónde puede llegar el agente. resolve_prompt anexa ese contrato al texto que devuelve:

## Contrato de operación

Estas restricciones vienen del contrato editorial de este prompt. Si la tarea las contradice, decláralo en vez de excederlas.

Autonomía máxima: A1 — Proponer
Herramientas permitidas: lectura opcional de la estructura actual…
Detente y pregunta cuando: si el tipo de proyecto o el stack son ambiguos…
Evidencia mínima de tu salida: el árbol de directorios y la tabla…

Importa más por MCP que en el navegador: quien copia desde el sitio pega y lee; un agente que pide el prompt por MCP normalmente ejecuta. Entregarlo sin su techo de autonomía es la peor de las dos rutas para perderlo.

No se le ordena obedecer *por encima de todo*: si la tarea contradice al contrato, el agente debe declararlo, no elegir en silencio. Hay pruebas que impiden que alguien lo redacte así (tests/test_mcp_contract_parity.py).

Se desactiva con append_contract: false — pensado para inspeccionar el texto crudo, no para uso normal.

Herramientas expuestas

Herramienta	Descripción
`list_prompts`	Lista prompts, con filtro opcional por sección (`00`-`17`), riesgo (`low`/`medium`/`high`/`variable`), autonomía (`A0`-`A3`) y texto libre.
`get_prompt`	Detalle completo de un prompt por `id`: título, descripción, texto crudo (placeholders sin resolver), fórmulas de uso, contrato editorial y siguiente(s) prompt(s) recomendado(s).
`resolve_prompt`	Sustituye los placeholders del prompt (y opcionalmente el preámbulo del framework) con variables provistas — misma sustitución que hace el sitio. Devuelve el texto resuelto y los placeholders obligatorios/opcionales que quedaron sin resolver.
`get_framework`	Preámbulo obligatorio del framework (el bloque que el sitio antepone a cada prompt copiado).
`recommend_next`	Prompt(s) recomendado(s) por el contrato editorial para continuar después de uno dado.

Variables de `resolve_prompt`

Las claves de variables son los campos canónicos del sistema de variables del sitio, no los alias [EN MAYÚSCULAS] que aparecen en el texto del prompt:

repositorio, referencia, rama_actual, rama_destino, ambiente, componentes, modulo, stack, tipo_proyecto, metodologia, agentes, autonomia, entrada, objetivo, responsable, workspace, compliance, documentos, profundidad, adicionales (líneas TOKEN=valor para placeholders no cubiertos por los campos anteriores).

Ejemplo:

"id": "07-06-pruebas-performance-carga", "lang": "es", "variables": { "repositorio": "org/mi-repo", "ambiente": "staging", "adicionales": "PATRON DE CARGA=1000 req/s durante 10 min" } }

Desarrollo

npm test    # node --test test/ -- 29 tests: dataStore, resolvePrompt, integración MCP real (InMemoryTransport)

Los datos (data/prompts-full.json) se regeneran desde la raíz del repo con python build.py — no editar ese archivo a mano. Cualquier cambio de contenido de prompts se hace en ai_sdlc_pro_prompts/*.md.

Alcance de esta primera versión

Se ejecuta en la máquina de quien lo usa (npx -y ai-sdlc-prompts-mcp, o node index.js desde el clon).
Transporte stdio únicamente — sin servidor HTTP.

AI-SDLC Prompts

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Developer toolsi

Common questions

Alternatives

GitHub

Desktop Commander

Cloudflare MCP

README from the maker

AI-SDLC Prompts — servidor MCP

Instalación

Ejecutar

equivalente a: node index.js

Configurar en Claude Code / Claude Desktop

Contrato de operación

Herramientas expuestas

Variables de resolve_prompt

Desarrollo

Alcance de esta primera versión

Variables de `resolve_prompt`