AV-MCP Automator

AV-MCP Automator

Middleware that uses Model Context Protocol and generative AI to automatically generate native Crestron Construct interfaces (.cuig/.cuib), enabling natural language creation of AV control UI components.

Category
Visit Server

README

AV-MCP Automator

Middleware basado en Model Context Protocol para la generación automática de interfaces nativas de Crestron Construct™ (.cuig / .cuib) mediante IA generativa.

Empresa: DACER S.A.C. — Miraflores, Lima, Perú
Practicante: Brayan Delgado Oblitas
Metodología: RUP adaptado (desarrollador único) — 14 semanas


Estructura del proyecto

AV-MCP_Automator/
├── docs/                   # Fases RUP: Inicio y Elaboración
│   ├── 01_Inception/       # Visión, casos de uso, requisitos, riesgos, glosario
│   └── 02_Elaboration/     # DAS, esquema JSON compilador, diagramas UML
│       ├── architecture/
│       ├── schemas/
│       └── diagrams/
├── src/                    # Fase RUP: Construcción
│   ├── client/             # Capa 1 — UI Streamlit
│   ├── server_mcp/         # Capa 2 — Servidor FastMCP + Compilador .cuig
│   │   ├── tools/          # search_tool, builder_tool, cuig_tool
│   │   └── templates/      # Plantillas Python por componente CH5
│   ├── core_ai/            # Capa 3 — Enrutador IA (Gemini → Ollama fallback)
│   │   ├── prompts/        # System prompts
│   │   └── schemas/        # Modelos Pydantic para validar JSON de Gemini
│   └── data_layer/         # Capa 4 — LanceDB + documentación fuente
│       ├── raw_docs/       # Docs .md de Crestron para indexar
│       └── lancedb_store/  # Base vectorial embebida (generada en runtime)
├── tests/                  # Pruebas unitarias e integración
├── deploy/
│   └── manuals/            # Manual de usuario y guía de despliegue (Fase Transición)
├── .env.example            # Variables de entorno requeridas
└── requirements.txt        # Dependencias Python

Inicio rápido

# 1. Clonar e instalar dependencias
pip install -r requirements.txt

# 2. Configurar variables de entorno
cp .env.example .env
# Editar .env con tu clave de API de Gemini

# 3. Indexar documentación en LanceDB
python src/data_layer/ingest.py

# 4. Iniciar servidor MCP
python src/server_mcp/main.py

# 5. Iniciar UI (en otra terminal)
streamlit run src/client/app.py

Stack tecnológico

Capa Tecnología
UI Cliente Streamlit (Python)
Servidor MCP / Compilador FastMCP (Python)
IA Principal Gemini 2.5 Flash-Lite (API)
IA Fallback Ollama + Llama 3.2 3B (Q4_K_M)
Base Vectorial LanceDB
Ecosistema destino Crestron Construct™ (.cuig / .cuib)

Documentación del proyecto

Ver docs/02_Elaboration/architecture/AV-MCP_Automator_Contexto_Proyecto.md para el documento maestro de contexto del proyecto.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured