Desktop Control

Render HTML/.eml emails in real Gmail, Outlook & Yahoo web clients and screenshot them

Local OCR and on-device screen reading for MCP clients (Claude, Cursor): read any window, locate elements to click, assert what's on screen. Apple Vision, no API keys, nothing uploaded.

Let Claude, Cursor, or any MCP client see and operate your Windows 10/11 desktop. 32 tools for screenshots, UI Automation, Chrome CDP, keyboard/mouse, terminal, with semantic discover-then-act targeting and per-action perception guards that avoid wrong-wi

Natural-language phone control for AI agents — CLI, MCP server, and agent SDK

Local-first cross-platform execution and research layer for AI agents with persistent PowerShell, durable checkpoints, live operator control, optional Windows UI, web research and YouTube research.

MCP server for native app testing — screenshot, OCR, click, type, find_text, template matching. macOS, Windows & Android.

Screenshots as a build step: keep the current design workflow and let ShipScreens use MCP or CLI for deterministic App Store + Google Play release screenshot ops.

MCP server that gives AI agents eyes on your terminal — PNG screenshots, visual diffs, GIF recording, and full keyboard/text interaction

MCP bridge: lets Claude Code (or any MCP client) build and run Ui.Vision RPA macros via the browser extension

npm launcher for the open-compute MCP server: model-agnostic computer-use tools (screenshot capture, canonical safety-gated actions, Windows UIA element targeting) over MCP stdio. Spawns the Python open-compute server (from GitHub).

MCP server for automating native Windows desktop apps — Playwright for Windows. Gives AI assistants (Copilot, Claude, Cursor) full control over WinUI3, WPF, WinForms, and Win32 apps with 55 UI automation tools. Built entirely with GitHub Copilot.

MCP-first browser primitives for AI agents — real eyes and hands on the web. Local-first. Vendor-agnostic. Yours to own.

CLI installer for Power BI Desktop MCP Server — auto downloads, installs and configures for Claude Desktop and Claude Code

Local MCP server that gives any AI agent safe cross-OS desktop control — the fallback execution layer for when APIs, CLIs, and direct integrations aren't available. Works with any tool-calling model (Claude, GPT, Gemini, Llama) on Windows, macOS, and Linu

Local-first desktop control MCP server (computer use): Rust host + Node launcher for safe app/window/input/screenshot automation on macOS and Windows

Open-source Computer Use for macOS. See and operate Mac applications through MCP or TypeScript, including native and Electron interfaces.

Capture polished DOM element screenshots for AI agents, CLI workflows, and MCP hosts.

Give AI eyes and hands on your desktop. ScreenHand is an open-source MCP server that lets Claude and other AI agents see your screen, click buttons, type text, and control any app on macOS and Windows.

Clickr — macOS screen measurement and input control MCP for Claude Code. Screenshot any display, click any global coordinate, type into any application.

Cloud Chromium browsers for AI agents — legitimate web access with live viewer, one-click human takeover, and a clean residential connection. MCP + A2A ready.