"Top 100 MCP Servers Ranked by Weekly Downloads" matching MCP servers:

Enables AI assistants to manage virtual machines, sandboxes, and dev environments through VirtualBox, Hyper-V, and Windows Sandbox, supporting VM lifecycle, ISO downloads, networking, and unattended installs.

Enables AI assistants such as Claude, Cursor, Continue, and Codeium to manage files and downloads on Synology NAS devices through secure authenticated sessions. Supports Docker, PyPI, stdio, Streamable HTTP, and WebSocket deployment modes.

Provision KYC-free, crypto-paid Nordic VPS and dedicated servers from any AI agent. Enables natural language hosting workflows including comparison, top-up, and provisioning of anonymous servers.

Enables API-token authenticated MCP access to Proxmox VE's HTTP API, exposing every endpoint for managing VMs, containers, storage, networking, and cluster resources. It also provides searchable API documentation, multipart uploads, and streamed downloads.

Comprehensive Synology NAS management through MCP, enabling file operations, downloads, backups, Docker, photos, VMs, snapshots, and more across up to 9 NAS units.

Self-hosted PaaS MCP server providing a write-capable control plane with over 100 tools to deploy, roll back, manage domains, and administer infrastructure, while ensuring agent permissions never exceed human RBAC.

Enables systematic investigation of VMware errors and events by correlating event timelines, ranking root-cause hypotheses, and suggesting next diagnostic steps.

Enables LLM agents to control NVIDIA Run:AI infrastructure by dynamically searching and executing over 426 Run:AI APIs through MCP tools.

A read-only MCP server for Proxmox VE that provides AI assistants with structured visibility into cluster nodes, guests, storage, and Docker workloads. It is designed to prevent any mutating operations by construction.

Enables Claude to manage Docker Compose containers by updating, running commands, and viewing status/logs.

MCP server for VMware vSphere, providing read-only access to inventory, monitoring, events, and alarms by default, with optional write and destructive modes for VM power operations, snapshots, cloning, reconfiguration, and migration.

An MCP server for managing Incus virtual machines through structured tools for command execution, file management, and snapshot operations. It enables AI agents to puppeteer VMs on a masternode by wrapping the Incus CLI.

Enables AI to observe and control the DOS game Master of Orion 2 by reading emulator memory and simulating mouse/keyboard input.

Enables MCP clients to manage disposable cloud Linux machines by creating and controlling them, executing commands, reading and writing files, creating snapshots, publishing ports, and issuing SSH tokens.

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.

A private MCP server that lets ChatGPT create, manage, and operate Box by ASCII Linux environments through secure MCP tools.

Minimal MCP server for Proxmox VE — 38 tools for nodes, VMs, LXC, storage, and snapshots. Read-only by default, single Docker image, multi-arch.

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.

An MCP server that enables LLMs to execute Python code on GPU-accelerated compute nodes within SLURM-managed HPC environments. It bridges local clients to remote clusters by launching JupyterLab sessions via SLURM jobs to facilitate high-performance notebook-based computation.

Enables programmatic control and AI-driven E2E testing of iOS virtual machines by exposing display, touch input, and navigation tools. It provides hardware key emulation, app navigation, and raw touch interactions with inline screenshot feedback for real-time visual context.

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.

Enables MCP-compatible clients like Claude Desktop, Claude Code, Codex, and local-model hosts to inspect Proxmox VE clusters, nodes, VMs, containers, storage, snapshots, and tasks, with opt-in write operations for starting, stopping, cloning, backing up, and migrating guests. Read-only by default, it supports both stdio and Streamable HTTP transports.

Lets an AI assistant check on a ZimaBlade or any Docker host over plain SSH (load, top processes, container stats, logs, disk) and restart only allowlisted containers. Nothing to install on the box.

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.

Enables AI assistants to interact with DDEV local development environments by querying databases, managing project states, and executing container commands. It provides comprehensive control over local services with a security-first approach using whitelisted operations.

Nido is a local QEMU VM manager. Install it on your computer from https://github.com/Josepavese/nido and run nido mcp via stdio, or use npx -y nido-mcp@latest mcp with QEMU installed locally. It manages VMs on that same computer; a server hosted by Glama cannot access your local VM inventory.

Enables AI coding agents to reverse engineer an operating system from its ISO and rebuild it component by component, exposing 39 tools over stdio for ISO fingerprinting, sandboxed QEMU VM lifecycle, PE analysis, API-surface dumps, syscall tracing, behavior diffs, component scaffolding, compat shims, app-compat testing, and knowledge-base search. It lets an agent survey a reference OS, generate clean-room specs and code, boot the rebuild, and test real applications against it.

Enables AI agents to run commands, read and write files, inspect containers and services, and check system health on remote Linux hosts configured in ~/.ssh/config, while blocking dangerous operations by default.

Enables AI-powered network engineering by providing natural language control over GNS3 network simulations. Supports creating projects, building network topologies, managing devices, controlling simulations, and analyzing network traffic through conversational AI interactions.