"Screenshot or Screen Capture" matching MCP servers:

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

A local Python MCP server for driving, perceiving, and rendering terminal programs, using a pluggable PTY and pyte screen model to let AI agents interact with real TUIs.

More than just an MCP server that covers the entire range of Docker management tasks, it helps you create workflows to easily manage your Docker environments at scale. It allows you manage multiple local or remote (TCP, TLS, SSH) docker instances and exposes things like logs and stats as resources so that you can monitor and triage all of them.

Give Claude Desktop full desktop control on Linux/X11: screenshot, mouse, keyboard, windows, clipboard, app launch. Zero-dependency MCP extension, MIT-licensed.

Provides transactional intelligence for AI agents, enabling safe tool execution with pre-flight invariant checks, sub-second filesystem snapshots/rollback, causal tracing, belief contradiction detection, and 15 native MCP tools for Claude Code.

Sandboxed Bash for Agents. Full state capture on every command.

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.

MCP server for terminal control enabling AI to manage terminal sessions via iTerm2 or tmux, with features like screen reading, keyboard/mouse input, and background execution.

Unofficial Powershell MCP server

A MCP server that enables AI assistants to control Android devices via ADB, supporting device info, screen control, input simulation, app management, shell execution, file transfer, and UI parsing.

An MCP server that provides full control over iTerm2 terminal sessions on macOS. It enables users to manage windows, tabs, and panes, run commands, read screen content, and interact with terminal sessions through Claude.

Provides full control of a macOS system, enabling AI agents to execute shell commands, run AppleScript, manage files and processes, and perform human-like GUI interactions such as clicking, dragging, scrolling, and typing, with a screenshot-based perception loop.

Give your AI Agent terminal access to your IBM i system via TN5250. ibmi-mcp is an MCP server that lets AI Agents like Claude interact with IBM i the same way a human would through a 5250 green-screen terminal.

Enables an MCP client to observe and control a text-mode DOS system via a Python bridge, supporting keyboard input and screen capture.

Enables launching and controlling real, visible Windows Telnet windows by reading their screen buffers and sending keyboard events, with session management and text-waiting capabilities.

Enables AI assistants to perform authorized WiFi security assessments, including network scanning, handshake capture, and password cracking, by executing aircrack-ng commands on a remote Kali Linux system via SSH.

Enables executing Bash commands, pipelines, and scripts across Windows, macOS, and Linux via MCP, with support for multiple runtimes, timeouts, working directories, and stream capture.

Manage local/SSH/WinRM remote hosts via MCP, providing tools for exec, filesystem, screen, process, serial console, and configuration.

Enables MCP-based communication with existing interactive terminal channels, such as shells or agent CLIs, by listing, reading, writing text, and sending control signals to tmux sessions without creating or managing them.

MCP server for Oracle Linux OS operations, providing tools for package management, kernel, storage, network, and security tasks via dbxcli.