"Using code execution to replace native tooling" 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.

Provides a local, isolated Linux VM sandbox for AI agents using Apple's Virtualization.framework, enabling fast command execution (~60ms) and package management without cloud costs.

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

Enables creation of ephemeral, polyglot development environments using Nix for on-demand execution of code with specific dependencies across Python, Node.js, Ruby, R, and Lua without cluttering the system.

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.

A server implementation that enables remote Python code execution in Unreal Engine environments, featuring automatic Unreal node discovery and management through a multicast network.

System Initiative provides AI Native Infrastructure automation that gives you clarity over your running infrastructure, control to change, automate, and integrate it, with conifdence

Enables AI assistants to create isolated Kubernetes Pod sessions for real-time shell command execution, file management, and Node.js code execution, with automatic TTL-based cleanup.

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 time-travel debugging for AI agent sandboxes using Firecracker microVMs, with tools for code execution, file operations, and VM snapshot/restore via MCP.

Facilitates isolated code execution within Docker containers, enabling secure multi-language script execution and integration with language models like Claude via the Model Context Protocol.

Persistent, secure LXC sandbox environments for AI agents with native MCP support.