"Information about sandbox environments or games" matching MCP servers:

A sandbox MCP server for testing and debugging MCP tools and interactions via the MCP Inspector.

Enables code execution in isolated Docker containers with persistent IPython, Node.js, or R kernels, supporting file import/export and cross-session transfers via MCP tools.

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.

Creates short-lived, offline JavaScript sandbox containers for safe code execution via MCP, with no network access and strict resource limits.

The Problem Modern distributed systems and AI agents require robust operational scaffolding. Simple CRUD apps or mock loops fail when subjected to real-world edge cases, asynchronous boundaries, and security constraints. The Solution An isolated execution platform for AI agents. An agent is given a broken service and a bounded toolset inside a disposable sandbox. Every command passes throug

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.

Execute scientific scripts (R, Python, GMT, LaTeX, Octave, Julia, etc.) in isolated, disposable containers with no host filesystem access.

Enables AI clients to manage and execute development commands within isolated Railway sandboxes, providing a remote shell, file read/write, and sandbox lifecycle management for running tests, builds, and repository operations.

Enables AI coding agents to work inside a disposable Windows guest desktop, where they can run shell commands, launch applications, inspect and operate native GUI controls, perform browser DOM actions, and transfer files. Fresh observations, PNG screenshots, and hashed artifacts let agents verify results without touching the host desktop.

Enables chat clients to execute real shell commands (apt install, curl, ffmpeg, Python) inside a disposable, per-conversation Debian container and hand resulting files back to the user via signed download links. Installed packages and processes are discarded when the container recycles, while files under /workspace persist.

This server gives AI clients a persistent, isolated Linux container in which the model can run any bash command as root with internet access, install packages and start long-running processes without command filtering. Files produced inside it can be handed back to the user as signed, expiring public download links suitable for PDFs, images, audio and video.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables AI agents to safely execute privileged commands by routing them to a human approver, who runs them outside the agent's context and returns the output to the model.

Enables MCP-compatible agents to execute bash and subprocess commands through a zero-dependency sandbox guard that blocks destructive system mutations, path traversals, reverse shells, and other unsafe execution patterns.

Enables agents to manage and operate macOS VM workspaces through authenticated MCP tools, including lifecycle control, command execution, job monitoring, and access to desktop connection and guest login details.

Enables AI coding agents to execute safe read-only shell commands immediately and to request one-time human approval before potentially destructive shell or file operations run. It integrates with clients such as Cursor, Claude Code, Copilot CLI, and Codex.

Enables AI services like Claude and Cursor to remotely control a Mac by executing shell commands, managing files, and running AppleScript for UI automation. Access is secured through OAuth 2.0 authentication and encrypted tunnels to protect remote interactions.

This is a secure Python code execution server that enables LLMs to run Python code safely in isolated Docker containers, supporting stdout capture and Matplotlib PNG generation.

Enables AI assistants to understand lab topologies, follow operational principles, and interact with real network devices through observable terminals while keeping private access information hidden.

Enables a coding agent to get short, token-efficient answers about a project through grouped searches, focused symbol or section reads, and bounded read-only script output, with safety limits on paths, secrets, commands, and response size.

Gives Amazon Quick Desktop real shell access outside its sandbox, running commands as your own user with login-shell environment, synchronous execution, background jobs, process-tree cleanup on timeout, and an audit log. A narrow pattern-based guard blocks a handful of destructive commands while ordinary work — including targeted recursive deletes — passes through.

Runs shell commands inside an existing microsandbox sandbox rather than on the Windows host, tracking the working directory and translating paths between the host project folder and the sandbox mount. Exposes tools for foreground or background execution with timeouts, output retrieval, killing processes, and listing them.

Runs git-bash (MSYS2) commands for AI agents on Windows from outside the agent's sandbox, so pipelines, command substitution, and subprocesses work. Exposes exec, bash_info, doctor, and policy tools with timeouts, output spilling, concurrency limits, capability-based command gating, and JSONL auditing.

A minimal MCP server that exposes a single tool to query local hardware information (OS, CPU, memory, architecture).

JSON-first Coreutils CLI for AI agents. 114 commands with sandbox, dry-run, and MCP zero-dependency server.

Runs AI-generated code in secure Firecracker microVMs with opt-in network policy enforcement, PII scanning, prompt injection defense, and audit logging. Exposes MCP tools for running commands, managing files, and the full sandbox lifecycle.

An MCP server that intelligently filters and compresses tool outputs to reduce context window usage, saving up to 90% of tokens by removing noise such as passing tests and redundant information.

Bridges the OpenAI Codex CLI app-server to MCP clients, letting agents launch and resume Codex coding sessions within a chosen workspace under configurable sandbox and approval policies. It exposes tools for sending prompts, long-polling task progress and live command output, approving or canceling runtime requests, and listing or reading past session history.

An MCP server that lets AI assistants inspect and control Asterisk and FreeSWITCH PBX systems, enabling natural language queries about live switch status, channels, registrations, and call control.