"Using ComfyUI on the web with cloud services" matching MCP servers:

MCP server for AI-controlled GPU VRAM management in ComfyUI, allowing Claude to monitor and control GPU state, manage model offloading, and start/stop ComfyUI.

Enables ChatGPT to access approved local Windows folders, run commands, control the desktop, and manage session history through a permission-bounded MCP server.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Enables management of Azure Cloud PCs using the Microsoft Graph API, allowing users to list available Cloud PCs in their tenant through Claude Desktop.

Connects ChatGPT Web to a self-hosted local coding workbench, enabling file editing, shell commands, Git/GitHub operations, multi-workspace management, code review, terminal processes, checkpoints, and optional Docker sandboxing.

Installs an agent on Linux hosts to allow shell commands, file edits, and service management through Claude.ai or ChatGPT via a secure outbound WebSocket connection.

Enables GUI automation by executing Python code with instrumented pyautogui, providing MCP-friendly output and inline screenshot delivery.

Enables cloud agents to securely operate local machine resources (files, commands, screenshots) via standard MCP protocol.

Provides tools for obtaining system CPU and memory statistics through FastAPI endpoints exposed via MCP.

Enables supervised, visible control of a Windows desktop from an MCP client, providing real mouse and keyboard input, screenshots, local safety controls, and a teaching mode for guidance without injection.

Enables remote server control via SSH through Claude, supporting command execution, file transfers, and multi-server management with both standard and streamable HTTP protocols.

Lets AI assistants understand what you're working on — current screen content, recent dictation, clipboard, and saved notes — running entirely on your own machine with nothing sent to the cloud.

Enables reading, writing, and manipulation of Bike outlines on macOS through natural language, using AppleScript for local document management.

Enables AI agents to capture and analyze screenshots of macOS applications, windows, or the entire screen using local (Ollama) or cloud-based AI vision models, with non-intrusive, fast screen capture via Apple's ScreenCaptureKit.

Inspect, manage, and kill local dev servers via MCP. Stop guessing what's on :3000. Five tools: list servers with framework detection, inspect ports, find zombies, diagnose conflicts, safe-kill with dry-run default. Local, no cloud, no telemetry.

Enables AI agents to start and stop full-screen recordings on macOS using FFmpeg, with control over quality, FPS, and audio.

This MCP server allows AI assistants to read, send, search, and manage emails in Apple Mail on macOS. It uses AppleScript to interact with the Mail app locally.

MCP server that exposes mDNS service discovery functionality via the Model Context Protocol, enabling LLMs to discover and query zero-configuration network services on the local network.

An MCP server that lets AI assistants manage an OpenMediaVault NAS over SSH using OMV's own RPC interface, covering disks, filesystems, shares, users, S.M.A.R.T. health, services, and configuration changes. It exposes a small set of generic tools to discover and call RPC methods, plus optional shell access.

Enables an MCP client such as Claude to inspect a Mac's battery, memory, CPU, GPU, disk, and most energy-hungry apps, and to shut down, restart, sleep, or lock the screen now or on a schedule with a cancellable 60-second grace period.