"Persistent" matching MCP servers:

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

Provides a persistent Docker computer with terminal, file editing, and optional desktop GUI control through a Three.js interface.

DockaShell is an MCP server that provides AI agents with isolated Docker containers for persistent shell access, file operations, and full audit trails, enabling autonomous development and self-evolving workflows.

A unified mesh control layer that provides 30 MCP tools for managing distributed infrastructure, enabling AI agents to execute commands, transfer files, and manage Docker containers across multiple nodes. It features persistent SSH2 connection pooling and cross-node configuration synchronization to unify disparate servers into a single interface.

Enables AI agents to operate a real, private, local Docker-based computer with durable files, terminal access, web research, and a persistent browser or desktop. It supports multiple agent clients via MCP or OpenAPI, with live viewing and human takeover.

Enables agents to create and manage persistent Dedalus Machines, wait until they are running, execute shell commands, and run diagnostics without manual polling.

MCP server providing AI agents with persistent shells, filesystem access, and multi-machine management backed by Docker containers or remote SSH hosts.

Provides ChatGPT with a persistent, VM-like Linux engineering workstation inside Docker, with root access, development tools, and a private nested Docker daemon.

Enables natural language management of Docker containers, images, networks, and volumes with support for both local and remote Docker engines. Features automated container composition, debugging capabilities, and persistent data management through an intuitive conversational interface.

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.