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

Lets agents play Doom-engine games (Freedoom, Doom, Doom II, Heretic) one turn at a time over network MCPL, taking actions like move, turn, goto, attack and use while receiving frames, events, bearings and map clearance. Enables people to watch each turn on the web, chat with the player, and replay or resume games that survive server restarts.

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.

Production-ready MCP server for secure Python code execution with artifact capture, virtual environment support, and LM Studio integration.

Automatically converts JavaScript modules into MCP-compatible servers, making any JavaScript function accessible to AI systems through secure sandboxing with automatic type inference.

MCP server allowing two agents to play chess or Connect Four against each other, with a live rendered board and emotion signaling.

A Model Context Protocol server that enables AI assistants to create, control, and interact with virtual desktop environments through E2B's secure cloud sandboxes.

Enables AI agents to create, manage, and execute code in isolated Firecracker microVM sandboxes via the MCP protocol, with support for sandbox lifecycle and file operations.

A secure Node.js execution environment that allows coding agents and LLMs to run JavaScript dynamically, install NPM packages, and retrieve results while adhering to the Model Control Protocol.

Provides a secure, isolated JavaScript execution environment with configurable time and memory limits for safely running code from Claude.

Enables local, Docker-isolated code execution across six programming languages including Python, Rust, and TypeScript. It features pre-warmed container pooling, persistent sessions, and built-in support for machine learning libraries.

Enables agents to investigate and remediate simulated incidents across fake services, with planted injections and fake secrets, for guardrailed tool-call evaluation and recovery.

Enables enforcing memory boundary compartmentalization and multi-tenant security isolation for autonomous agents via a deterministic, zero-dependency Python skill. Seamlessly integrates with Claude Desktop, Cursor, and other MCP-compliant clients to execute isolation policies through structured JSON-RPC requests.

Enables developers and AI agents to enforce per-tenant security isolation for autonomous agents by compartmentalizing memory boundaries and managing sandboxed tenant execution. It exposes this deterministic, dependency-free guard through a native MCP server that plugs into Claude Desktop, Cursor, and other MCP-compliant clients.

Provides a native MCP-compatible autonomous agent that decomposes general tasks, runs multi-modal web and sandbox execution loops, and self-corrects toward goal resolution using sensory and ambient inputs.

A Model Context Protocol (MCP) server for Claude Desktop that connects to 302AI's API services, allowing users to integrate and leverage 302AI capabilities through a structured communication interface.

Enables remote Python code execution via the Model Context Protocol for secure, real-time lab scenarios and sandbox testing. It allows AI clients like Claude and Cursor to execute and evaluate code within a virtual lab environment.

Enables natural language control of ArduPilot drones via MAVLink, supporting arm, takeoff, mode changes, and mission uploads.

Enables delegating coding tasks to sandboxed agents, returning changes as auditable diffs for human review before applying or discarding them.

Enables LLMs to execute Python code in isolated sandboxes with file operations and MCP integration, supporting multi-round execution and plot capture.

Implements a Model Control Protocol server integrated with Google Gemini LLM, providing a flexible framework for building AI-powered applications.

Enables agents to get fast, calibrated probabilistic answers from Jev (Typesafe AI) to yes/no, scale, or choice questions about provided material, without using a generative model.

Routed is a universal local router for Agent Skills across AI coding environments.

GATE verifies whether an AI agent still has valid delegated authority at execution time. It provides live revocation checks, signed authority evidence, alternate delegation paths, and explicit ALLOW, DENY or UNKNOWN decisions. Integrates with MCP tools through a trusted effect-boundary guard. Open-source Developer Preview with Free sandbox and live network onboarding.

An improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. This lets Claude remember information about the user across chats.

A stdio MCP server that lets Claude Code delegate coding tasks to an OpenCode instance (optionally attached to an internal LLM gateway), with follow-up replies, status polling, output/diff retrieval, cancellation, and cleanup handled in a single session. It supports managed or attach modes, sandbox and approval policies, parallel fan-out delegations, and read-only review workflows.

An MCP server that lets LLM agents autonomously play retro games by driving a real OpalEmu emulator in a Playwright-controlled browser, exposing tools for loading ROMs, controlling buttons, and capturing screenshots.

A Python code execution sandbox based on IPython and Docker. Stateful code execution, file transfer between host and container, configurable network access.

Enables running code against tests in an isolated sandbox to obtain PASS/FAIL verdicts with signed, offline-checkable certificates, and generating verified code with attached certificates after execution against derived tests.

An MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.

Bridges MCP (Claude Code) to ACP (Devin), enabling Claude Code to delegate autonomous tasks to Devin with permission and filesystem sandbox controls.