"How to use the browser console" matching MCP servers:

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.

Legacy MCP server for console automation that preserves interactive sessions, a 40-tool command/test surface, and legacy protocol adapters for local/remote execution. Intended only for migrations to RunBeacon 3.0.

Enables AI assistants to execute Ruby console commands (Rails console, IRB, etc.) with persistent session support for interacting with Ruby/Rails applications through natural language.

Enables AI assistants to fully interact with console applications, monitor output, detect errors, and automate terminal workflows across multiple sessions. Similar to how Playwright works for web browsers but for command-line interfaces.

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.

Exposes persistent, stateful remote Bash sessions to AI agents via SSH, enabling command execution with preserved working directory and environment.

MCP server for controlling PNETLab v6 network labs via natural language, enabling topology creation, node management, config push, console interaction, and link fault injection.

AgentBridge is a local MCP server that lets Claude Code delegate coding tasks to external CLI workers like Codex and Antigravity. It assembles structured prompts, runs the workers with git snapshotting, and returns compact structured results without running its own models.

Enables Claude Desktop to control serial-port devices like network craft ports, radios, rotators, and microcontrollers by sending commands and reading responses until a prompt or available output.

Enables AI assistants to run, manage, and debug BSD/Illumos VMs through natural language. Supports creating FreeBSD, OpenBSD, NetBSD, and OmniOS VMs, executing commands inside them, accessing console logs, and managing snapshots.

Runs commands on machines you cannot SSH into by publishing steps to a transport the far side already reaches (git, file share, S3, relay), then reads back a log with every line timestamped in UTC. Seven tools cover send, status, logs, stall detection and a pre-flight check.

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.

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.

Bridges Claude AI to a live Unreal Engine 5 editor session, enabling natural language control of scene inspection, modification, logging, source search, console commands, and C++ class scaffolding.

Enables AI agents to run PowerShell commands and manage Windows services without intrusive console windows, while also supporting remote execution via SSH and WinRM.

Enables operating a FiveM server by sending commands to the FXServer console through txAdmin and returning the console output, with tools for status, players, and server control.

Enables AI assistants to interact with Cisco routers and switches over serial console connections, handling prompt detection and pagination.

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.