LUZMCP
Provides tools to query and change IoT lamp status through the Flask REST API, enabling remote monitoring and control of devices.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
๐ก LUZMCP โ Sistema IoT com MCP Server & PWA
Sistema distribuรญdo para monitoramento e controle remoto de lรขmpadas/dispositivos IoT em tempo real. A arquitetura conecta um Progressive Web App (PWA) moderno, um servidor MCP (Model Context Protocol) para integraรงรฃo com Agentes e LLMs, uma API REST Flask e um microcontrolador simulado no Wokwi executando MicroPython.
๐ฎ Demonstraรงรฃo Online (Teste Agora Mesmo)
Vocรช pode testar todo o sistema funcionando ao vivo sem precisar instalar nada:
Abra o Simulador de Hardware:
๐ Acessar Simulador Wokwi
(Clique no botรฃo verde de Play โถ๏ธ para iniciar a placa e ligar a conexรฃo Wi-Fi).Abra o Painel de Controle (PWA):
๐ Acessar Painel IoT Control (PWA)
(Funciona no computador e no celular. No celular, vocรช pode selecionar "Adicionar ร tela inicial" para instalar como app).Interaja com as Lรขmpadas:
Clique no botรฃo de L1 โ O LED Vermelho no pino GP10 acende na simulaรงรฃo.
Clique no botรฃo de L2 โ O LED Azul no pino GP11 acende na simulaรงรฃo.
Desligue os interruptores no app para apagar as luzes correspondentes.
Related MCP server: Philips Hue MCP Service
๐๏ธ Arquitetura do Sistema
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Clientes โ
โ โข PWA no Celular / Computador (Firebase Hosting) โ
โ โข Agentes de IA / LLMs (Claude, Gemini, Antigravity) โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
โโโโโโโโโโโโโโโโโโดโโโโโโโโโโโโโโโโโ
โ โ
(Modo IA / Tools) (Modo Web Direto)
โผ โผ
โโโโโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโโโโ
โ MCP Server (Py) โ โ API REST Flask (Py) โ
โ Transporte SSE / RPC โโโโโโโโโโโบโ (PythonAnywhere) โ
โโโโโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโฌโโโโโโโโโโโโ
โ
Polling HTTP (1s)
โ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโ
โ Raspberry Pi Pico W โ
โ (MicroPython) โ
โโโโโโโโโโโโโฌโโโโโโโโโโโโ
โ
Pinos GP10 e GP11
โ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโ
โ LEDs L1 (Vermelho) โ
โ LEDs L2 (Azul) โ
โโโโโโโโโโโโโโโโโโโโโโโโโ๐ ๏ธ Tecnologias Utilizadas
Microcontrolador / IoT: Raspberry Pi Pico W simulado no Wokwi, programado em MicroPython com comunicaรงรฃo HTTP via
urequests.Backend: Python / Flask hospedado no PythonAnywhere, com suporte a CORS nativo e gerenciamento de estado dos perifรฉricos.
Camada MCP: Model Context Protocol SDK (
mcp), expondo as ferramentasobter_status_lampadasealterar_status_lampadavia Server-Sent Events (SSE).Frontend / PWA: React 19, Vite, TypeScript, Tailwind CSS e Lucide Icons, hospedado no Firebase Hosting.
๐ Estrutura de Diretรณrios
.
โโโ app.py # API Flask existente com rotas /micro e /comandos
โโโ mcp_server.py # MCP Server expondo Tools IoT via protocolo SSE
โโโ wokwi.txt # Cรณdigo MicroPython para o simulador Wokwi
โโโ firebase.json # Configuraรงรตes de deploy no Firebase Hosting
โโโ pwa/ # Aplicaรงรฃo frontend PWA
โ โโโ src/
โ โ โโโ App.tsx # Lรณgica hรญbrida (MCP + API Direta) e interface
โ โ โโโ main.tsx # Ponto de entrada React
โ โโโ package.json # Dependรชncias do frontend
โ โโโ vite.config.ts # Configuraรงรตes de build e proxy local
โโโ README.md # Documentaรงรฃo do projeto๐ป Como Rodar o Projeto Localmente
1. Prรฉ-requisitos
Python 3.10 ou superior instalado.
Node.js 18 ou superior instalado.
2. Rodando o Servidor MCP (Python)
pip install -r requirements.txt
python mcp_server.pyO servidor MCP inicializarรก ouvindo conexรตes SSE na porta 8080.
3. Rodando o PWA em Desenvolvimento
cd pwa
npm install
npm run devAbra http://localhost:5173 no seu navegador. O frontend conectarรก automaticamente ao MCP Server local via proxy /sse.
๐จโ๐ป Autor
Desenvolvido por Marlon Kipson
GitHub: @marlonkipson95
Repositรณrio: marlonkipson95/LUZMCP
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
This server cannot be deployed
Maintenance
Related MCP Connectors
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
AgentReady Tools is a searchable catalog of more than 250 APIs, MCP servers and developer tools that AI agents can use, each with agent-readiness checks (docs, auth, OpenAPI, MCP support). Search by task, get tool details and related tools, and read or share field notes from other agents in the Agent Community. Remote MCP endpoint: https://agentready-tools.com/mcp
Connect any AI agent to 1,000+ apps and 27,000+ actions through one remote MCP server (OAuth).
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI agents to control Home Assistant smart home devices via MCP, with zero external dependencies. Supports calling services, getting states, and looking up service parameters.MIT
- AlicenseNot gradedqualityDmaintenanceEnables control of Philips Hue lights through the Model Context Protocol, providing tools for turning lights on/off, setting brightness and color, and retrieving light status.1Apache 2.0
- FlicenseNot gradedqualityDmaintenanceExposes MCP tools that enable remote LLMs to query local Docker containers, OS processes, and system services in real time.-
- AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible AI agents to read room temperatures and control smart home lights via natural language.1MIT