"All items" matching MCP servers:

Enables AI assistants to scan a Mac for reclaimable disk space and safely move selected items to the Trash, with dry-run defaults, protected paths, and confirmation before permanent deletion.

Enables Claude AI to open files and directories with system default applications or specified apps, and reveal items in macOS Finder.

MCP server allowing any and all command execution over CMD

Read-only disk analysis and reversible cleanup for macOS 13 and later. Scans the Mac and shows what is actually taking space, then moves only the items you approve to the Trash — no rm -rf, and every operation is undoable.

Connect AI with any macOS app. Deep integration with native apps like Calendar, Mail, Notes, plus UI control for all applications. Works with Claude, Cursor, Raycast, and any MCP-compatible AI.

Simple MCP Runner makes it effortless to safely expose system commands to language models via a lightweight MCP server—all configurable with a clean, minimal YAML file and zero boilerplate.

Full computer control for AI agents on macOS — see, click, type, scroll via MCP. Works with any app, all processing on-device with PII protection.

Enables capturing screenshots of all connected monitors with automatic JPEG compression and multi-platform support including WSL environments. Supports quality adjustment and image resizing through simple natural language commands.

Enables AI agents to see and control your desktop with tools for screenshots, clicks, typing, and more, all locally on macOS and Windows.

An MCP server that enables viewing all screens and controlling mouse and keyboard, allowing clicks anywhere and text input.

Enables an AI assistant to measure macOS disk usage, investigate unfamiliar files and folders, identify cleanup candidates, and prepare numbered cleanup proposals that move approved items to the Trash only after server-side path checks.

MCP server that gives AI agents access to your Maus clipboard on macOS, enabling them to write clean text into history, search, and manage clipboard items locally.

Enables MCP clients to connect to saved Bizagi Modeler .bpm files, detect the local installation, open models, and retrieve diagram entities and connections with refresh after saves, all within a user-authorized folder.

Automatically discovers all scriptable macOS apps and generates MCP tools for them, giving AI access to apps like Mail, Calendar, and Finder without any configuration.

Enables AI agents to scan a developer machine for disk space hogs, audit git worktrees for stale or orphaned ones, re-check individual findings, and run allowlisted cleanup actions as dry runs unless explicitly confirmed. Risky items are reported with warnings and refused by default.

Give any AI full control of your desktop. Mouse, keyboard, screenshots — all through the Model Context Protocol.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables an agent to drive an Android phone attached via USB by reading the screen, deciding next steps, executing actions, and verifying results, all through adb.

macctl is an accessibility-first macOS desktop automation MCP server that lets AI clients see the screen, inspect app accessibility trees, control mouse/keyboard, manage windows, and run commands, all behind tiered permissions and audit logging.

Enables AI assistants to scan local disks for developer caches, large unused videos, and old logs, present candidates for approval, and move only approved items to the operating system trash so they can be restored while protecting system folders.

Enables any MCP-compatible agent to query a local OpenRhyme activity timeline, search history, and issue control commands over stdio while keeping all data on-machine.

Reports the local user's current activity and idle state, including idle duration, idle threshold comparison, and timestamps, so agents can decide whether to wait for user feedback or keep working autonomously. All activity data is collected on-device through operating-system APIs and returned only to the connected MCP client.

Gives AI agents safe, bounded, non-blocking access to Linux sysadmin inspection tasks, including CPU, RAM and disk healthchecks, memory-safe log tailing with regex filtering, and user-level systemd service and timer auditing. All operations run without sudo or unrestricted root shells, avoiding interactive pager hangs and context window flooding.

Enables any AI agent to perceive and control a Windows desktop through live screen capture, OCR, and safety-gated mouse/keyboard actions via a local HTTP API and MCP.

Enables AI agents to observe and operate a real Windows or Linux desktop like a human — snapshotting screen geometry, active window, OCR text and normalized UI elements, then clicking, typing, scrolling and managing windows with built-in verification and recovery. Backends are chosen automatically per action (UIA/AT-SPI → OCR → vision → PyAutoGUI), so browsers, IDEs, office suites and canvas apps are all controllable without any browser-automation MCP.

Gives AI assistants local access to a Mac's clipboard history, letting them search past clips and lists, read a clip in full (including text recognized inside screenshots), and place a clip back on the system clipboard for the user to paste. Everything runs over 127.0.0.1 with explicit user approval, and assistants cannot delete clips or see items concealed by password managers.

An MCP server that enables AI assistants to send native macOS notifications with automatic project detection and categorization. It includes logging capabilities for all notifications to provide an audit trail of system alerts.

Exposes a Windows desktop WeChat 4.1.6+ client as MCP tools, letting assistants read and search chat history by date, send messages or files to friends and groups, list contacts and group members, and view or post Moments. All actions run through UI automation without reverse-engineering hooks, returning structured JSON results that MCP clients such as Claude Desktop, Cursor and Cherry Studio can call.

Enables any MCP-compatible AI, whether in the browser or running locally, to create and edit projects, run terminal commands and long-running jobs, and optionally use Docker, all guarded by a policy engine, workspace jail, authentication, and audit logging.

All-in-one homelab management MCP server. Docker monitoring, volume backup/restore (with compose and env files), Wake-on-LAN, network scanning, and multi-server SSH management.