"Information on agent swarm architecture" matching MCP servers:

A production-ready MCP server for Docker Swarm that provides full control over services, stacks, configs, and secrets with smart context preservation to reduce tool clutter.

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 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.

Gives a coding agent its own Docker-hosted Linux desktop with XFCE, Chromium, Blender, LibreOffice, GIMP and a sudo shell, exposing tools for screenshots, mouse and keyboard input, window focus, shell commands, file read/write, opening URLs or GUI apps, and headless Blender renders. The agent can watch and drive that desktop live from a browser while working on the shared project folder.

Read-only MCP server for one Docker host: list containers, inspect (without env vars), logs with time windows and search, stats and events. Cannot start, stop, remove or exec.

Enables users to list GKE clusters, describe virtual machines, and retrieve billing information through MCP read tools, without applying production changes.

An MCP server for managing home lab VMs and PNETLab topologies, enabling AI agents to power VMs, handle snapshots, and verify device configurations with explicit allowlists and confirmation gating.

Enables AI agents to create and control isolated Android emulator sessions through MCP, including app launch, UI interaction, screenshots, and audio/screen recording. It supports session-keyed device allocation, recording retrieval, and optional local-only WebRTC viewing.

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.

Provides MCP tools for managing disposable Docker sandboxes that let AI agents safely execute commands in isolated, ephemeral environments.

MCP server for automating VLP lab VM operations, exposing VM management tools to AI agents like Cursor and Claude Code.

Enables AI-assisted DevOps by exposing scoped, role-based tools to inspect and remediate a Docker app stack, with audit logging and allow-listed commands for safe incident response.

MCP server for managing Proxmox VE hosts, providing VM health reports, alerts, and a chat interface via terminal or Cursor.

A Linux system monitoring MCP server that provides real-time information on CPU, memory, disk, network, processes, Docker, security, and more via MCP tools.

Enables inspection and operations on a local host through two action-router MCP tools, covering Docker daemon and container state, Compose projects, host information, allowlisted read-only command execution and file search, ZFS pools, and systemd journal logs.

Free, cross-platform VM orchestration for AI workflows with built-in MCP integration, sandboxed code execution, and compliance-ready architecture (SOC 1/2/3, HIPAA, ISO 27001).

Enables MCP-capable agents to execute generated Python, Node.js, or shell code inside disposable, network-isolated Docker containers with strict resource, filesystem, privilege, and time limits, returning structured results and errors.

Enables read-only inspection and confirmed mutation operations on a single VPS over SSH, including host health, Docker, Compose, Swarm, firewall, and system debugging tools.

Enables AI agents to control local Android virtual devices managed by DroidLume, including device lifecycle, app management, UI input, screenshots, and diagnostics through structured MCP tools.

Enables MCP clients to create, update, destroy, and list Vagrant (VirtualBox) VMs on a remote host through natural-language tool calls over Streamable HTTP, handling fixed-IP allocation, Vagrantfile rendering, and Ansible-based configuration. Its provisioner architecture allows other infrastructure backends such as Terraform or public clouds to be added without changing existing code.

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

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.

MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.

Enables coding agents to deploy and manage game server containers on Edgegap, from creation through player connection, without manual API reference.

A read-only server that enables AI agents to triage Kubernetes CronJobs in a single tool call: whether runs happened and stayed on schedule, whether durations are trending slower or overrunning, which jobs have silently stopped succeeding, and why a given run failed, with evidence and stated basis for each verdict. It also lists active runs and recent failures while enforcing namespace allowlists and no write access.

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.

Let your AI build and run a whole app on your computer: an online shop, website, booking app or AI helper. It creates the parts, starts them, checks they work and fixes problems.

MCP server for managing FeiNiu fnOS NAS via AI chat. Supports system status, Docker container operations, and disk information retrieval.

Enables AI agents to boot and drive headless QEMU virtual machines by sending keystrokes, capturing screenshots, and reading or writing the serial console without SSH or a guest agent.

Enables AI assistants to manage VMware Fusion virtual machines on macOS using the vmrun CLI, including starting, stopping, and snapshot operations.

No-KYC crypto VPS hosting with an MCP server that lets AI agents provision VPS programmatically. Pay with USDC/USDT on Base and Ethereum, no accounts or verification required.

Provides tools to list, create, power on/off, and delete VMs on vCenter or ESXi hosts using natural language.

Enables AI agents to deploy and manage Docker containers on your own machine via MCP tools, providing public HTTPS URLs through free Cloudflare quick tunnels.

Run AI agents in VM-isolated sandboxes on your Mac.

Enables users to manage standard AutoDL container instances through natural language: powering them on (including a no-GPU mode), powering them off, and checking instance and background job status. When GPUs are out of stock, power-on requests keep retrying in the background with exponential backoff until the instance starts.

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.

MCP server and CLI for IBM HMC REST API, enabling AI agents to inventory Power systems, manage LPARs/VIOS, and submit jobs like power on/off, with tools for adapters, storage, networking, and more.

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 Codex to browse, search, read, download, and upload files on a connected NAS, query storage and container status, and manage containers, download tasks, and applications via the official unc CLI.

Enables AI assistants to run shell commands, read, write, edit, search, and stream files on remote SSH servers and Docker containers, including nested multi-layer chains, without installing any runtime on the target hosts. It auto-injects a self-contained Go helper with adaptive zstd compression for fast transfers and process control.