"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.

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

MCP server that enables Claude to control your computer, similar to Anthropic's computer use but easy to set up locally.

Pixel-level browser automation MCP server that drives a real Chrome browser using screenshots as vision input and OS-level mouse/keyboard as output, evading anti-bot detection.

An MCP server for comprehensive browser automation and full local PC control via shell commands and Python execution. It enables tasks like web navigation, file system management, and remote access through SSE with token authentication.

Enables AI agents to see and operate a Windows PC through mouse, keyboard, screenshots, OCR, window control, and shell commands.

Enables MCP agents to automate real GUI applications on headless desktops, providing background mouse/keyboard control, window/process management, screenshots, and safe human handoff without disturbing the user's desktop.

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.

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

Enables Windows desktop automation through strict UI Automation control operations and explicitly opted-in native keyboard/mouse input, plus screenshots, recording, action scripts, OCR, and process management.

Enables MCP clients to observe and control the Windows desktop through the UI Automation accessibility tree — no vision model required — by exposing tools for reading windows and interactive elements, clicking, typing, scrolling, shortcuts, PowerShell, screenshots, virtual desktops, web scraping, file operations and persistent memory, including background-window control without stealing focus. An optional agent mode adds a single natural-language task tool that runs the full upstream agent loop when an LLM provider is configured.

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

Serves a local dsh workspace as a protected Streamable HTTP MCP endpoint, letting authenticated web AI agents read, search, patch, inspect, and operate the project, with optional shell commands, LSP support, and public tunneling.

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

Provides 146 MCP tools for AI agents to control macOS, including screenshots, mouse, keyboard, window management, app automation, file system, OCR, and built-in app semantics like Calendar, Mail, Safari, Music, Messages. Enables full control over macOS through natural language.

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.

Enterprise-grade macOS MCP server that gives AI agents eyes, hands, and a terminal, enabling screen capture, mouse/keyboard control, shell commands, and file operations.

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.

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

A local MCP runtime for macOS and Windows that enables ChatGPT to read, edit, search, run tests, and capture screenshots in your local project folder while keeping your source code on your machine.

Provides secure filesystem access for AI models through the Model Context Protocol with strict path validation, file operations, directory management, and system command execution within predefined directories.

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

Enables AI assistants to create isolated Kubernetes Pod sessions for real-time shell command execution, file management, and Node.js code execution, with automatic TTL-based cleanup.

The m2m-mcp-server-ssh-client provides a unified MCP server interface, securely connecting via SSH to the m2m-mcp-server-ssh-server back-end which aggregates MCP servers. This setup offers secure, single-point access to diverse remote tools using robust SSH key-based authentication.

An MCP server that enables AI assistants to execute shell commands and manage files on remote servers via SSH. It supports recursive directory uploads, archive extraction, and direct file creation from text content.

A self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls.

Enables MCP-compatible AI clients to connect to a Windows machine for file operations, PowerShell execution, Git inspection, task management, memory, and skills.

Enables AI agents to securely use real secrets (API keys, database passwords) by requiring human approval for each release, ensuring secrets never enter the model's context.

MCP Bridge is a local-first Linux/Windows desktop app connecting ChatGPT to approved files and Chrome through authorized OpenAI tunnels, with optional shell tools. The Glama-hosted v0.1.0 release is a restricted READ-ONLY documentation demo: five tools can access only bundled public examples, not your computer, browser, credentials, shell, or files.

Local Dev Doctor turns an unfamiliar development checkout into an evidence-backed diagnosis. It discovers how the project is meant to run, checks safe prerequisites, and executes only the exact probe that a user approves.

Enables a private ChatGPT app to remotely control a Windows PC through file operations, PowerShell, screenshots, mouse and keyboard input, clipboard, and Chrome browser automation.

Enables AI agents to ask users for credentials, secrets, and sensitive data through local browser forms that the model never sees, then resolve and use those values only at approved points of use. Also supports blind web capture, SSH key provisioning, and writes to .env files, SQL databases, and APIs, with the agent receiving only structural results.

Problem: MCP clients can't efficiently use Xcode CLI tools because the build and simulator listing commands return more than 50k tokens, exceeding MCP limits. Solution: MCP tooling using progressive disclosure with intelligent caching.

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.

Self-hosted MCP server that gives AI assistants a real Linux development environment: file editing, shell commands, tmux terminals, and browser screenshots, with bounded access through a project registry and write gates.

LocalBridge MCP is a bridge between an online AI chats and your computer. Most online AI chats can reason, and write code, but they normally cannot touch the local files, terminals, and scripts that make real work happen. This gives a trusted assistant a controlled doorway into a machine you own, so it can inspect files, edit text, search a project, run tests, use Git, and operate a shell.

Enables AI agents to operate Windows through persistent PowerShell sessions, dual-channel desktop perception, element-level UIA, CDP browser control, verified actions, and failure self-healing.

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.

Verified control of the whole desktop for agents on Windows and Linux: apps with no API, windows, shell, browser. MCP server + CLI + REST API.

Gives AI assistants eyes and hands on your desktop, letting them view and capture the screen, click, type, use the clipboard, run shell commands, and execute multi-step tasks with a single per-task authorization while keeping context small via a local state file.