"How to generate HTML code from Figma design files" matching MCP servers:

An MCP server to create secure code sandbox environment for executing code within Docker containers.

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 AI agents to run untrusted, model-generated Python code in a locked-down throwaway Docker container with enforced isolation and resource limits. Supports starting, checking, and stopping asynchronous runs while returning structured status reports without exposing the host, network, or Docker controls.

Enables headless control of a DOSBox-X guest, including memory reading and patching, framebuffer capture, input injection, and live code tracing without interfering with the host desktop.

Enables running arbitrary JavaScript code in isolated Docker containers with on-demand npm dependency installation, allowing for ephemeral script execution and long-running services with controlled resource limits.

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 managing GNOME Boxes virtual machines through libvirt/virsh, including lifecycle operations, snapshots, screenshots, and capability-gated keyboard, mouse, clipboard, and drag-and-drop interactions.

Enables running arbitrary JavaScript code in isolated Docker containers with on-the-fly npm dependency installation, supporting both ephemeral one-shot executions and persistent sandbox environments.

A secure Docker-based environment that allows AI assistants to safely execute code without direct access to the host system by running all code within isolated containers.

Connects AI agents to microsandbox for creating lightweight sandboxes, executing code, managing files, and monitoring resources.

Enables AI agents to spin up disposable Tenki microVM sandboxes in seconds and use them to run code, manage files, run git commands, and expose preview URLs.

MCP server that integrates with Coolify to let AI assistants manage Coolify instances via a clean toolkit wrapping the official REST API.

MCP bridge for Nemeton — control native macOS virtual machines (Apple Virtualization.framework) from Claude Desktop, Claude Code, or any MCP client. 50+ tools across VM lifecycle, snapshots, console, files, networking, and host metrics. Bridge open-source (MIT), Nemeton app is commercial.

Linux sandboxes for AI agents, each a Firecracker microVM. Run code, keep files, pause and wake with memory kept, snapshot and fork.

Extensible MCP server for managing a homelab from Claude AI, enabling control of VMs, snapshots, services, and files via natural language.

MCP server for generating and configuring development containers from devcontainer.json files, enabling management of devcontainer environments through tools like devcontainer_up, devcontainer_exec, and cleanup.

Enables users and LLMs to execute Python code, install packages, run terminal commands, and upload files in isolated Docker containers, returning outputs and HTTP links to generated files through an SSE interface.

Provides comprehensive management of TrueNAS SCALE instances through 278 actions across 18 categories using a token-efficient hierarchical tool design. Users can perform tasks like storage management, service configuration, and system monitoring while benefiting from built-in safety confirmations and read-only dashboard resources.

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 AI agents to inspect pending updates and service health for Proxmox VE VMs and containers, then take snapshots, apply official updates, reboot, and roll back under tag-based permissions and human-confirmed risky actions.

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.

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.

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

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.

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.

A self-hosted MCP server providing a governed interface for AI agents to interact with local Docker infrastructure, featuring a two-phase confirm protocol for state-changing operations and append-only audit logging.

Read-only MCP server to list your SkyNode servers and check their status (IP, state, region, expiry). It does not modify or control servers.

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 AI agents to interact with Kubernetes clusters through progressive disclosure, where agents discover TypeScript modules via filesystem, write and execute code, and receive summarized console output for cluster management tasks.

An MCP server that lets Claude monitor and manage a TrueNAS box in plain English. It is deliberately read-only, providing tools to check alerts, storage pools, snapshots, services, and more.

Enables AI coding agents to safely execute code, run tests, and build projects inside disposable Docker sandboxes, protecting the host machine through enforced isolation, filesystem snapshots, and network controls.

MCP server that wraps the vmm-api CLI to enable listing and managing VMM network topologies through natural language.

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.

Read-only VMware vCenter/ESXi monitoring. 8 MCP tools for VM inventory, host status, datastore capacity, cluster info, alarms, events, and VM details. Code-level enforced safety — no destructive operations exist in the codebase. Supports vSphere 6.5–8.0. Works with local models via Ollama/LM Studio.

MCP server for managing VMware Horizon VDI environments via the Horizon 8 REST API, enabling AI agents to monitor sessions, manage pools, and perform operations like logoff, reset, and image push with safety previews and audit logging.

MCP server for Nutanix Prism Central v4 REST API, enabling AI agents to list and inspect VMs, control VM power state, list clusters, read alerts, and list subnets.

A Model Context Protocol (MCP) server that interfaces with the Apache YuniKorn Scheduler, allowing AI agents to observe and reason about Kubernetes batch workload resource management, queue hierarchies, and application states.

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

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.