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

自托管的MCP服务器，在Docker沙箱中提供命令执行、后台长任务、大文件传输和多沙箱自动管理，专为AI助手设计。

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

Provides an AI agent with authenticated shell and file access to a sandbox host, plus a restricted gateway for safe deploys on a production host via forced SSH commands.

Gives an LLM a secure local workspace where it can write files, execute Python in a locked-down Docker container with no network access, and run read-only SQLite queries. Lets the model run, debug, and fix its own code without risking the host machine.

Enables AI coding agents to audit and sweep away transient scratch directories, bloated test caches, and forgotten probe scripts in a workspace, with dry-run previews to guarantee nothing tracked or production-related is touched. It also detects zombie background dev servers still holding common ports like 3000, 5173, and 8000.

Provides tools to monitor host system health including CPU load, disk usage, and network status while enabling file system management tasks like searching and moving files. It includes built-in safety guards to prevent operations on critical system directories.

Enables local sandbox synchronization, allowing agents to upload and pull files between their machine and a sandboxed box, while providing all the standard ParallelSandbox tools via stdio.

Enables users to ask natural-language questions about a local folder's contents, including file names, sizes, and timestamps, with rollups by type and age and cleanup suggestions for stale or large files. It returns metadata only and cannot read, move, or delete files.

Reads and searches local email archives (.mbox or .eml) with full MIME parsing, enabling queries about senders, subjects, dates, and bodies while keeping all data on your machine.

Searches and browses local Claude Code and Cowork session histories stored on your machine, enabling questions about past work without uploading data.

Mac file and terminal tools for local AI clients, plus an opt-in ChatGPT Developer Mode relay. Checked edits, bounded reads and real exit codes. Free MIT agent; OpenAI listing under review. Owner-level access, not a sandbox.

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

Enables users to access local files, manage persistent notes via CRUD, fetch URLs, inspect system information, and analyze or transform text through MCP tools.

Bridges VS Code on Windows with remote Linux servers via SSH, enabling AI assistants to interact with remote development environments.

Runs as an MCP server providing file system operations, shell execution, and system information tools, allowing Claude or any MCP client to edit files and control the machine.

This server provides robust media metadata detection, AAC audio stream extraction, and EXIF data reading using only pure JavaScript. It is optimized for execution in highly restricted environments where traditional binaries like FFmpeg or Python are unavailable.

Provides core filesystem, shell, search, and listing tools with a path sandbox, supporting HTTP and stdio transports.

Enables LLMs to interact with Python environments, execute code, manage files, and handle packages through the Model Context Protocol.

An MCP server for 7-Zip archive operations (list, extract, create) with dual-engine architecture and sandbox security features. Note: currently a learning project and not yet functional.

Enables creation and management of UTF-8 with BOM encoded files optimized for Windows build environments. Provides file encoding conversion, detection, and template support for C++ and PowerShell files to prevent Korean character encoding issues.

For people who want their AI to run the build, read the error and check the dev server itself, instead of pasting output into chat. Works with Claude Desktop (one-click installer), Cursor, Claude Code and Cline. Runs locally over stdio or HTTP, no telemetry. A seatbelt for everyday mistakes, not a sandbox.

A Model Context Protocol server that allows LLMs to interact with Python environments, execute code, and manage files within a specified working directory.

A headless server that enables reading and sending Gmail emails through API calls without requiring local credentials or browser access, designed to run remotely in containerized environments.

Enables AI assistants to list directories, read, write, and search files within a locked root directory, using resolve-then-validate path checks, size caps, and binary detection to prevent sandbox escapes.

Enables storing durable AI memories linked to local JSON or text sources, automatically superseding outdated structured values, flagging ambiguous changes for review, excluding expired information, and preserving revision history in a local SQLite database.

Enables AI agents to securely read, write, and list files and run shell commands inside dashboard-whitelisted sandbox directories. It provides API-key authentication, firewall controls, and preinstalled development tools for connecting MCP-compatible clients.

A read-only MCP server that lets local AI agents inspect open Mac windows, browser tabs, PDFs, clipboard contents, Finder selections, and Messages history so they can answer questions about what the user is currently viewing.

Enables Claude to read and analyze project schedule files in OmniPlan (.oplx) and Microsoft Project (.mpp) formats, answering questions about tasks, milestones, resources, and progress.

Enables AI agents to control Hydra Launcher programmatically — search games, manage downloads, configure Proton, organize library, and more via 46 MCP tools.

MCP server that allows AI agents to read, search, summarize, and answer questions about local PDF, DOCX, XLSX, and TXT files through five tools.