"How to obtain a diff from a GitLab repository" matching MCP servers:

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

Enables saving files and folders to a local NAS over NFS with automatic share discovery, smart mounting, and seamless file transfers.

Enables AI agents to control and interact with a local Windows computer through authenticated MCP tools, including file operations, shell commands, process management, HTTP requests, and system/media inspection.

Enables AI agents to securely connect to and manage remote servers via SSH, with tools for running commands, file operations, log inspection, service management, and system monitoring under configurable access controls and audit logging.

A local agent that monitors your system clipboard, automatically uploads copied images to Supabase Storage, and replaces the clipboard content with the public URL for immediate sharing.

Enables AI assistants to diagnose, troubleshoot, and manage PC settings on Windows, macOS, and Linux through natural language commands.

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

Lets MCP clients discover and run AppleScript or JavaScript for Automation (JXA) to control macOS applications, inspect the system, or reuse scripts from a bundled knowledge base.

A Model Context Protocol server built with FastMCP that provides tools for retrieving the current local date and time. It allows LLMs to access precise temporal information directly from the host environment.

A local MCP server that exposes Mobile AI Agent capabilities from the WebADB browser as MCP tools, allowing external AI clients like Qoder and OpenClaw to control connected phones through natural language tasks, screenshots, device status, and memory management via a WebSocket relay.

Pre-alpha P2P remote-control app with a local stdio MCP bridge for paired computers. Users build from source; platform support and host-side approvals apply.

Enables an AI agent to read and configure OpenDeck stream controller setups through natural language, covering keys, dials, profiles, Multi and Toggle Actions, app-based profile switching, and plugin management. Every change is staged, previewed as a diff, applied only after confirmation, and backed up so it can be undone.

Allows Claude desktop app to execute terminal commands and edit files on your computer through MCP, with features including command execution, process management, and diff-based file editing.

Enables MCP clients such as Claude to read temperatures, fan speeds, power and clocks from a CoolerControl daemon, and to change fan profiles, fixed duty speeds, modes, functions, alerts and custom sensors through its REST API. Write operations are gated behind a token with write access, with an optional minimum-duty floor guarding against accidentally stopping a pump or fan.

Enables AI agents to see and operate a real USB-connected iPhone from a Linux Docker host — taking screenshots with region zoom, reading the element tree, tapping, swiping, long-pressing, typing text, pressing hardware buttons, listing/launching/terminating apps, and opening URLs. Automatically recovers from replugs and crashes, re-signs its automation agent before expiry, and falls back to a signing-free HID path on newer iOS.

Enables server operations and AI application deployment via 16 MCP tools, including container management, disk diagnostics, and GitHub repository search with one-click deployment, through natural language.

Enables AI platforms to manage a norc account’s cron jobs and machines and review run history directly from chat, including declarative job syncing.

Controls Android and iOS devices from AI agents through a token-efficient MCP server, enabling observation, tapping, typing, gestures, navigation, assertions, and safety-gated actions.

An MCP server that enables AI assistants like Claude to manage Unraid servers through natural language. Install it from Community Applications and control your homelab from any MCP-compatible AI client.

Enables an MCP-capable agent to operate a heterogeneous cluster of Debian/Armbian Linux nodes over SSH from a single inventory, inspecting status and logs, managing packages, services, files, storage and NFS, and deploying new capabilities to nodes through installable modules. Built-in cluster tools fan out to nodes by explicit names, roles or tags with bounded concurrency, while modules can be installed on compatible nodes and run on demand or as systemd services.

Enables Claude to read and search through iMessage, SMS, and RCS conversations, including mixed-protocol group chats with Android users. It decodes binary message data from the macOS Messages database to provide a comprehensive view of message history.

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.

Provides a ping tool to check connectivity and measure latency to any hostname or IP address across platforms.

A macOS MCP server that enables safe computer use by redacting password fields from screenshots, requiring explicit consent before clicks or typing, and logging all actions to an append-only audit file; it provides 12 tools for screen capture, UI inspection, and input control.

Enables voice-controlled local automation and laser engraving, allowing users to generate engraving previews and G-code from spoken text and send jobs to a laser engraver after confirmation.

MCP server that enables AI to see and control a physical computer via a JetKVM device for screen viewing, mouse/keyboard input, media mounting, and power management.

Gives a coding agent its own Docker-hosted Linux desktop with XFCE, Chromium, Blender, LibreOffice, GIMP and a sudo shell, exposing tools for screenshots, mouse and keyboard input, window focus, shell commands, file read/write, opening URLs or GUI apps, and headless Blender renders. The agent can watch and drive that desktop live from a browser while working on the shared project folder.

Enables AI agents to control a Linux optical drive tray as an emotive actuator, with tools for status, motion primitives, emotion choreographies, and diagnostics.

Enables AI agents to verify a human is physically present by ejecting the PC's optical drive tray and detecting when a person manually closes it within a configurable timeout.

Enables Claude Code to control a Windows desktop via screenshots, mouse, keyboard, and window/display enumeration, reusing the native binding from the Claude desktop app.