"Servers Offering MCP Prompts as Prompt Primitives" matching MCP servers:

MCP server that exposes fleet-aware KVM primitives for AI agents to control TinyPilot devices, including screen capture, keyboard input, mouse events, and device selection.

Provider-neutral MCP server for managing VirtualBox, VMware Fusion, and VMware Workstation, offering tools for VM lifecycle, configuration, snapshots, guest operations, networking, and artifact resolution.

Enterprise MCP server for Proxmox VE, offering 298 tools to manage VMs, containers, storage, cluster, firewall, and more via natural language.

Connects Claude Desktop to any Kubernetes cluster, enabling natural language queries for diagnostics and operations such as listing pods, viewing logs, scaling deployments, and more.

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.

Enables Claude Code to manage Hetzner Cloud servers, including creating, deleting, powering on/off, and rebooting servers, as well as managing SSH keys and listing resources.

A virtual Linux desktop as an MCP server, shipped in Docker. Agents drive screen, mouse, keyboard across any GUI — browsers, IDEs, office suites, Wine/Windows apps, legacy software — many in parallel.

Fork, break, and revert real VirtualBox VMs as MCP tools; drive GUI-only guests through the hypervisor (screenshot, click, type, keys) with nothing installed in the guest. Windows host with VirtualBox.

MCP server for Proxmox Backup Server. Exposes datastore status, snapshot inventory, garbage collection, verify, and prune over the PBS REST API as 13 LLM-callable tools.

An MCP server that exposes Runloop Devbox operations as tools, enabling AI agents to create and manage Linux sandboxes, execute commands, edit files, snapshot disks, and drive interactive PTY sessions.

Enables AI agents to explore and operate OpenShift/Kubernetes clusters, offering read-only tools for projects, pods, logs, and resources, with opt-in higher modes for scaling, restarts, applying manifests, and deletions under safe-by-default guards.

Enables MCP clients to diagnose Proxmox VE clusters — quorum and HA state, Ceph and ZFS health, backup coverage audits, task failures, pending updates and node evacuation planning — with answers returned as findings and recommended steps. VM power, snapshot and migration operations are available but disabled by default, requiring a preview and a bound confirmation token before anything executes.

Private MCP server exposing the ascii Box API as shell and file tools, letting agents like ChatGPT or Claude drive Linux boxes.

Wraps the Docker Engine API as MCP tools for container and image management. Reduces token consumption by providing typed tools with default summaries and field selection.

Enables AI agents to see and drive Kasm Workspaces desktops by starting and stopping sessions, taking screenshots, and performing clicks, typing, key presses, and scrolling through MCP clients or as a native Hermes Agent plugin.

Governed AI-ops MCP server for Nutanix Prism Central v4 REST API, offering 47 read/write tools for clusters, VMs, storage, network, catalog, data protection, alerts, and LCM upgrades with built-in audit, budget, and risk-tier governance.

Enables AI agents to capture high-quality screenshots from running QEMU virtual machines using the QEMU Machine Protocol (QMP), automatically discovering VMs and returning screenshots as PNG images.

Enables an AI agent to boot and control an Android emulator — tapping, typing, scrolling, inspecting screens, reading logs and installing APKs — and to record those interactions as replayable, CI-ready test flows. Actions are captured by element text or id rather than coordinates, so the saved tests survive layout changes and rerun without the agent.

Exposes a HashiCorp Nomad cluster as MCP tools for AI agents, enabling read-only inspection of jobs, allocations, nodes, and deployments, with optional write operations like stopping jobs, scaling task groups, restarting allocations, and registering jobs.

An MCP server that exposes Proxmox VE node/cluster as tools for MCP clients, enabling management of VMs and containers including power control, resource reconfiguration, snapshots, and backups.

Enables MCP-compatible AI assistants to inspect and manage local or remote servers in plain language, covering system health, Docker containers, services, ports, disks, scoped files, and read-only database queries over key-only SSH. Write actions such as container restarts, file edits, and allowlisted dev commands require client approval.

Enables AI assistants to manage Nutanix infrastructure via Prism Central and Prism Element APIs, including VM operations, cluster management, networking, and as-built report generation.

Enables AI-powered creation, configuration, and management of DevContainer environments using natural language prompts. Supports 11+ templates for popular development stacks and provides container lifecycle operations through VS Code, Cursor, or any MCP-compatible editor.

Enables policy-gated control of Hyper-V virtual machines on Windows through a single local stdio server, covering VM inventory, power, checkpointing, PowerShell Direct guest diagnostics and file transfer, synthetic keyboard/mouse console input, serial consoles, ISO media mounting, and serial WinDbg preparation. Every mutation requires an explicit VM allowlist and per-capability flag, with read-only operation as the default.

This MCP server enables MCP clients such as Claude Desktop to run LLM-generated code in a secure, isolated sandbox across multiple container backends and programming languages.

MCP server that exposes Podman host management as tools, allowing natural language control of containers, images, volumes, networks, and pods. Includes an administrative console with safety profiles for gated access.

MCP server for Android emulator automation via ADB.

Enables coding assistants to drive iOS Simulators and Android emulators or USB devices for React Native and Expo work, including taking screenshots, reading app and device logs, opening deep links, installing builds, and launching or relaunching apps. It also supports Android-specific actions such as adb reverse for Metro, opening the dev menu, and tapping or typing on screen.

Enables AI assistants to provision and manage cloud infrastructure and AI/ML workloads—such as GPUs, nodes, storage, networking, databases, Kubernetes, and training/inference resources—through natural language. It also provides a universal REST tool for authenticated access to the underlying cloud API.

A comprehensive Model Context Protocol (MCP) server that exposes 216 tools, 7 resources, and 10 runbook prompts for every OpenShift 4 cluster operation an SRE, developer, or operator could need — all driven by an LLM.