convez.ai
MCP ServerAutomaçãoIntermediário
bala-2305

Echo MCP Server

bala-2305/echo-mcp

Automação de GUI completa para LLMs com visão, mouse, teclado e browser

Ver no GitHub
BomPluginScore · de 0 a 100

Um MCP server Python que fornece automação GUI autônoma para clientes LLM, permitindo que a IA interaja diretamente com a tela, mouse, teclado e navegador do computador. Suporta visão computacional, OCR, automação de janelas, controle de sistema e browser automation via Selenium.

Instalação

$npx convez-ai bala-2305/echo-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
6
Forks
0
Acompanhando
0
Saúde
100%
Último commit
há 2 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Automação desktop controlada por IA (cliques, digitação, navegação)
  • Extração de texto e elementos visuais da tela
  • Automação de navegador web e preenchimento de formulários
  • Controle de aplicações e processos do sistema

Veredito

Echo MCP oferece um conjunto robusto de ferramentas para automação de desktop e web via IA. Requer Python 3.12+ e é otimizado para Windows; ideal para tarefas repetitivas que envolvem interação com UI, mas exige cuidado com segurança em ambientes de produção.

README

A tradução para o português deste README ainda está na fila.

Echo MCP Server

PyPI Version Python Version License PyPI Downloads GitHub MCP

A Model Context Protocol (MCP) server that provides autonomous GUI automation capabilities to LLM clients (like Claude Desktop). This tool allows an AI to interact directly with your computer's screen, mouse, keyboard, and browser.

Features

  • Computer Vision & OCR: Extract text from screen regions and find UI elements visually.
  • Mouse & Keyboard Control: Perform clicks, typing, hotkeys, and precise movements.
  • Window Management: Focus, minimize, maximize, and query open windows.
  • System Automation: Manage processes, execute system commands, adjust volume, and check system health.
  • Browser Automation: Full web browsing capabilities (Selenium) for navigating, finding elements, extracting text, and clicking.
  • File System: Read/write files, list directories, download files.

Setup Instructions

1. Environment Requirements

  • Python 3.12 or higher
  • Windows (recommended for PyAutoGUI compatibility)

2. Installation

You can install the package directly from PyPI (https://pypi.org/project/echo-mcp/):

pip install echo-mcp

3.Configuration

You can Configure your AI apps/IDE to make use of the mcp server by running the following command

python -m echo_mcp.config

This will launch a CLI based setup wizard which help you to configure your AI apps/IDE to use the mcp server. You will need to restart the app/IDE for the changes to take effect.

Available Tools

The server provides a comprehensive suite of tools spanning multiple categories:

Mouse & Keyboard

  • mouse_click, mouse_double_click, move_mouse, mouse_drag, mouse_scroll, get_mouse_position
  • type_text, press_key, hotkey

Screen & Vision

  • take_screenshot, get_screen_size, get_text_at_coords, find_text_on_screen, click_element

Window & Process Management

  • list_all_windows, focus_window, maximize_window, minimize_window, get_window_geometry, close_all_windows_by_title, get_active_window_info
  • list_processes, kill_process, get_process_stats, wait_for_process

System Utilities

  • system_power, set_volume, get_system_health, get_disk_usage, ping, list_network_interfaces
  • launch_application, get_environment_variable, get_clipboard, set_clipboard, wait

File System

  • list_directory, read_file_content, write_to_file, delete_file, create_directory, download_file

Browser Automation

  • browser_open, browser_close, browser_navigate, browser_get_url, browser_get_title, browser_get_page_source
  • browser_find_element, browser_click, browser_fill_form, browser_extract_text
  • browser_screenshot, browser_scroll, browser_execute_script, browser_wait_for_element

Security Warning

Giving an LLM control over your mouse and keyboard is powerful but risky. Only run this server with prompts you trust, and never leave the automation unattended while active.

Ver o original no GitHub

Bom para

Relacionados