"Understanding How to Use a Browser" matching MCP servers:

An MCP server that lets an AI agent use a real terminal the way a person does: type, press keys, click, read the screen, take a screenshot.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables agents to interact with CLI applications like vim, htop, and gdb by sending key inputs and capturing terminal output through tmux sessions.

Enables coding agents to observe and control an authorized Android phone over ADB through MCP tools and a JSON CLI. It supports UI inspection, screenshots, taps, swipes, typing, key presses, app listing, and launching.

Enables control of an attached Android phone over ADB, including screenshots, taps, typing, key/chord input via a virtual HID keyboard, UI inspection, and device information without root.

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

A low-level computer-use MCP server that exposes raw desktop control (mouse, keyboard, shell, windows, processes, screenshots, etc.) to MCP clients like Claude Code and Codex.

Enables an AI to delegate work to secondary Antigravity CLI accounts, running jobs in parallel with dependency (DAG) scheduling, file read/write declarations, warm multi-turn sessions, account quota tracking and compact result collection. Users simply describe their request in natural language while the AI plans and the server executes — no hand-written workflow JSON required.

Local + remote terminal interaction control MCP Server. Lets AI agents control interactive TUI programs the way a human would.

Converts any Python Click or Typer CLI into an MCP server automatically — zero-code transformation that introspects CLI commands and exposes them as MCP tools.

Enables Claude to fully control a Windows desktop with native screen capture, low-level input injection, game-grade input, and play-testing capabilities.

A production-grade macOS MCP server exposing 33 tools for full desktop automation, including mouse, keyboard, screenshot, clipboard, and window control.

MCP server that routes Claude Desktop chat into Claude Code, enabling headless execution and terminal handoff with session continuity.

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.

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

An MCP server that lets Claude query Google's Gemini CLI as a sub-agent. Get second opinions, verify information, and cross-reference answers between AI models.

Enables Claude Code to interact with Linux X11 desktops by performing mouse actions, keyboard input, and capturing screenshots. It provides a suite of tools for automation tasks such as clicking, typing, and zooming on specific screen regions.

Retired. This MCP wrapper is no longer maintained. Check is now a Claude Code hook: npx @golproductions/check@latest --install. 120 free messages a day. Details: golproductions.com/check

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

Exposes Creatio CLI (CLIO) commands as tools for AI agents to manage Creatio environments. It enables users to perform environment health checks, restart web applications, and execute raw CLI commands through a stateless HTTP transport.

Wraps Kali Linux penetration testing tools for authorized security assessments, driven by a local LLM via LM Studio.

A simple MCP server that exposes a terminal tool, allowing AI agents to execute shell commands.

Read-only MCP server for TrueNAS Scale debugging, providing k3s tools for kubectl operations and whitelisted midclt calls for system info, apps, and pools.

Enables an MCP client to see and drive a Hyprland/Wayland desktop by taking cropped, downscaled screenshots, reading the compositor's window tree, and sending absolute pointer and keyboard input mapped back to global layout pixels. It also exposes off-screen tmux sessions, background task runners, and DevTools-driven Chrome tabs for work that needs no window focus.

An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret. Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output

Enables an AI assistant to read and control your real, logged-in Safari browser tabs, with a local model gating every write action for safety.

Controls local purplemux (tmux + LLM workspace manager) from Claude Code/Codex, enabling cross-LLM orchestration by managing workspaces, tabs, terminals, and Electron browser via 16 tools.

Enables ChatGPT web to use local tools like file reading, command execution, and patch application through an MCP server over OpenAI Secure MCP Tunnel.

A local-first secrets vault for MCP clients that lets AI assistants use secrets by injecting them into child processes, without the plaintext ever entering the model's context.

What Chrome DevTools MCP is for the browser, tui-mcp is for the terminal. Launch any TUI app, take screenshots, send keystrokes, read text - works with any framework.

Enables agents to run SweetScape 010 Editor Binary Templates and Scripts headlessly against local files. It provides tools to locate the editor binary, execute templates or scripts, and use controlled exit behavior for compile and runtime failures.

Enables MCP clients such as Claude and Cursor to control an isolated cloud machine with a real browser, shell, filesystem, and web access, so agents can navigate pages, click and type, run commands, manage files, and search or fetch web content.

SSH Session MCP fills a gap in the MCP ecosystem by offering a persistent shared SSH PTY runtime, not just stateless command execution. It features browser collaboration, input locking, safe/full execution modes, async command tracking, configurable policy rules, and multi-device profiles. Ideal for remote development, embedded systems, infrastructure workflows, and hardware control scenarios.

A MCP server enabling LLMs to roll dice

Enables AI agents to run, monitor, and manage Cypress tests with features like test discovery, screenshot handling, and multi-browser support.

Enables AI agents to look up stored logins by URL, name, or alias and use them without seeing the secrets, injecting authentication into HTTP requests, running commands with credentials in the environment and scrubbed output, and fetching 2FA codes, subject to per-credential policies and user approval.

Enables MCP clients on macOS to perform bounded read-only filesystem operations and a narrow allowlist of process diagnostics over STDIO or authenticated loopback Streamable HTTP. It excludes file writes, arbitrary shell access, GUI/browser automation, and remote relay.

Headless local stdio MCP server for board-debug operations, allowing compatible clients to use tools for firmware debugging and board management.

Exposes Laravel development tools (artisan, migrations, config, schema, logs) as MCP tools for use with compatible clients.

An MCP server that enables running CLI for Microsoft 365 commands through GitHub Copilot Agent, allowing users to interact with Microsoft 365 services using natural language.