"How to access a web browser" matching MCP servers:

Provides AI agents with isolated virtual desktops containing a real Chromium browser, enabling them to see, click, type, and navigate like a human, with features like snapshots and remote control.

A simple MCP server that allows accessing and executing shell commands on a VM machine through a web-based terminal interface, with automatic tunneling to make the VM accessible from anywhere.

MCP server for building and driving VMware Workstation VMs from an AI agent, enabling unattended OS installs, guest command execution, file transfer, screenshots, and fleet management.

A Python-based server that enables AI assistants to interact with an Unraid server through the official Unraid GraphQL API, providing read-only access to system information, Docker containers, VMs, storage, and more.

This project is intended as a both MCP server connecting to Kubernetes and a library to build more servers for any custom resources in Kubernetes.

Enables AI agents to operate a real, private, local Docker-based computer with durable files, terminal access, web research, and a persistent browser or desktop. It supports multiple agent clients via MCP or OpenAPI, with live viewing and human takeover.

A powerful, lightweight Model Context Protocol (MCP) server built in Python that enables Artificial Intelligence assistants (Claude Desktop, Cursor, Antigravity, Claude Code, etc.) to manage and monitor your Proxmox VE cluster using natural language.

Enables AI agents to dynamically spawn, route to, and manage ephemeral containerized sandboxes on Kubernetes without requiring Custom Resource Definitions or cluster-level operators.

A VMware ESXi/vCenter management server based on MCP (Machine Control Protocol), providing simple REST API interfaces for virtual machine management.

Enables AI agents to fully control an Android emulator via MCP, including UI interaction, screenshots, APK installation, logging, and clipboard access, with optional live browser viewing for humans.

Enables AI clients to manage Huawei eNSP simulated network devices, execute CLI commands, apply configurations, and perform network diagnostics through natural language, with topology upload and visualization via a web UI.

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 code-mode MCP server for the Unraid 7.2+ GraphQL API that exposes search and execute tools, allowing LLM agents to introspect and call any GraphQL field via sandboxed JavaScript.

Enables MCP clients to rent GPUs from ParalonCloud using natural language, including browsing available GPUs, starting and stopping rentals, and retrieving connection URLs.

An MCP server that gives LLM agents full API access to a VMware Cloud Foundation 9.1 estate, exposing 8,931 operations through eight tools with automatic authentication, async task tracking, and write safety.

Install and manage a self-hosted XNS Relayer — S3-compatible distributed object storage — conversationally over stdio. 15 tools cover prerequisites, account registration, install, claim, health, VPD configuration, S3 verification, CLI credentials, settings, restart, and backups.

Enables AI coding agents to safely run commands, install dependencies, test, and modify code inside disposable, policy-enforced Docker sandboxes isolated from the host, returning results and diffs.

GenieACS-MCP is a Go-based MCP server that bridges any GenieACS (TR-069 ACS) instance, exposing device data, firmware management, and CPE actions (reboot, parameter refresh, firmware download) over JSON-RPC

A Model Context Protocol server for the resQ emergency response system that integrates with digital twin simulations and coordination engines. It allows users to trigger simulations, generate deployment strategies, and monitor real-time drone status for incident response analysis.

Enables AI coding agents to safely execute commands, run tests, and modify project files inside disposable, policy-enforced Docker sandboxes that are isolated from the host machine and its credentials.