"Using npx to run tools directly without requiring an API" matching MCP servers:

Enables coding agents to list and boot iOS Simulators and Android Emulators, capture screenshots, drive device interactions through accessibility snapshots, and end sessions.

Manage and monitor Hadoop clusters via Apache Ambari API, enabling service operations, configuration changes, status checks, and request tracking through a unified MCP interface for simplified administration. * Guide: https://call518.medium.com/llm-based-ambari-control-via-mcp-8668a2b5ffb9

Provides Docker management tools for AI agents, including inspecting containers, images, Dockerfiles, and Compose configurations.

Enables AI assistants to manage Coolify infrastructure including servers, applications, databases, deployments, and 80+ one-click services through 98 comprehensive tools for both cloud and self-hosted instances.

MCP server for the Agent Platform API, enabling management of sandbox environments through MCP protocol. Exposes tools to interact with sandbox lifecycle operations such as start, stop, and status checks.

Expose Nutanix V4 APIs as tools callable by AI assistants — Claude, Cursor, and any MCP-compatible client.

Open-source MCP server for managing Hetzner Cloud infrastructure with two management layers: * Layer 1 — Hetzner Cloud API (35 tools): Server power control, metrics, snapshots, backups, firewalls, DNS zones and records, rescue mode, server rebuild and rescale. Works even when the server OS is unresponsive. * Layer 2 — SSH (25 tools): Service management (systemd), Nginx config and reload,

Provides read-only, governance-audited operations for OLVM and oVirt 4.5 engines, enabling inventory, health, capacity, and diagnosis queries over MCP and CLI with audit logging and budget guards.

Governed XCP-ng operations via Xen Orchestra REST — VM-health, SR-usage, backup-failure, and patch-state RCA, with unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback.

AI-powered Veeam Backup & Replication operations MCP server with tools for managing jobs, restores, sessions, and repositories, featuring built-in governance, audit logging, and safety controls.

Governed Kubernetes operations for AI agents with 15 MCP tools, audit logging, policy engine, and safety features.

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.

Governed Docker + Portainer container-host operations (non-Kubernetes) — restart-loop, resource-pressure, and image/volume-bloat RCA, with guarded lifecycle writes, unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback.

AI-powered MCP server for managing Proxmox VE VMs and containers with built-in governance, audit logging, and reversibility.

Enables an AI agent to view and control VMware vSphere VM consoles—screen, mouse, and keyboard—through vCenter, without installing anything in the guest.

An MCP server that lets AI agents run PHP unit and integration tests inside Docker containers without local PHP or Composer.

An OpenAPI-driven MCP server for Proxmox VE that provides 2 generic tools to execute any of 480+ API operations dynamically, plus tools for executing commands inside VMs and containers, saving ~95% tokens.

A read-only MCP server that lets Claude query a VMware vCenter environment through the vSphere REST API, listing virtual machines, ESXi hosts, clusters, datastores, networks, datacenters, resource pools, and folders. It issues only GET requests and can run over stdio or authenticated Streamable HTTP, so inventory questions can be answered without any risk of changing the environment.

Enables AI assistants to run Kali Linux security tools in an isolated Docker container for tasks like network scanning, port checking, and service enumeration.

Provides secure access to containerized build environments for software projects, enabling AI assistants to execute builds, run tests, manage git operations, and inspect build artifacts without requiring local installation of dependencies.

Enables managing Docker containers (run, list, stop, remove, view logs) through Claude Desktop using natural language commands.

Enables an AI agent to run and inspect containers, build and pull images, manage volumes and networks, drive Compose projects, clean up, and run self-checking practice labs. Startup modes restrict it to read-only, labs-only, or full Docker control with confirmation before dangerous operations.

Provides secure, disposable, resource-bounded container sandboxes that let AI agents create and inspect files, run shell commands with timeouts, and perform Git operations without exposing the host environment.

An MCP server that lets AI agents manage virtual machines across local and cloud targets, with tools to create machines, run commands, transfer files, and clean up ephemeral instances via natural language.

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.

MCP server for controlling VMware Fusion/Workstation virtual machines via vmrun CLI, providing 32 tools for VM lifecycle, guest execution, and file operations without requiring a REST API daemon.

Provides programmatic access to Xcode functionality, enabling AI assistants to create, build, test, and manage iOS/macOS projects directly.

An MCP server that enables interaction with development containers through the devcontainers CLI, allowing users to start, run commands in, and execute arbitrary shell commands inside devcontainers.

Enables an AI agent to see and control the screen of an already-running macOS virtual machine over VNC, exposing four tools: screenshot, click, type_text, and key_press. This lets the agent drive a disposable VM's UI directly with its own model, without touching the real desktop or running a separate agent loop.

Enables AI coding agents to manage cloud containers, create and edit files, run commands, and deploy projects directly.

Enables AI coding tools to deploy apps and databases, run VPS servers, buy domains and edit DNS, and send email through natural-language requests across Container, VPS, Domain, and Email APIs.

An MCP server that lets agents such as Claude, Cursor, and Codex operate a CapRover server, installed with npx or Docker and defaulting to a readonly safety mode. It is planned to expose the CapRover API as named tools and as Code Mode search/execute operations, with access modes and confirmation for destructive calls.

Enables agents to deploy, run, expose, inspect, and manage isolated cloud environments, including databases, caches, browsers, GitHub-hosted apps, and arbitrary OCI images, via MCP tools.

Enables AI assistants to browse and, when explicitly permitted, manage QuickCloud infrastructure — VMs, dedicated servers, firewalls, load balancers, storage, databases, email relay, websites and DNS — through tools generated from the provider's live API catalogue. Read-only by default, with writes gated behind an opt-in flag and per-call confirmation using your own API key.

Enables AI assistants such as Claude, Gemini, and GPT to connect directly to VMware ESXi and vCenter hosts over stdio JSON-RPC. Provides full virtual machine lifecycle management (create, clone, delete, power on/off) plus real-time CPU, memory, storage, and network performance monitoring, with API key authentication and SSL/TLS support.

Enables AI agents to safely inspect Kubernetes cluster inventory through read-only tools for listing nodes and pods, without exposing secrets or mutation operations.

MCP server that discovers Korean e-Government and financial websites and launches them in a clean disposable Windows Sandbox (or macOS macSandbox) without requiring security software installation. It handles search and sandbox execution, leaving authentication and actual tasks to the user.

Enables a restricted AI agent to run risky commands in a fresh, offline Windows Sandbox guest without access to the rest of the host, with a broker validating every request over an ACL-protected named pipe.

Exposes tools over stdio that let an AI agent create disposable Docker sandboxes to run commands and stream output, read and write files, and take snapshots, roll them back, fork them, list, and destroy them. It tells the model to snapshot before risky changes so failed attempts can be undone or explored in parallel on self-hosted infrastructure.

Enables MCP-compatible AI clients to run curated Kali Linux security tools such as nmap, gobuster, nikto, sqlmap and netcat inside an isolated microVM sandbox. Commands execute as asynchronous jobs with readable output, cancellation and persistent per-workspace storage, with configurable network, CPU and memory limits.