#sandbox

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

Create a remote sandbox that can execute code/run commands/upload and download files. 创建远程沙盒，可以执行代码/运行命令/上传下载文件

Run code in secure sandboxes hosted by E2B

MCP server for

Mirror of

An MCP server to create secure code sandbox environment for executing code within Docker containers. This MCP server provides AI applications with a safe and isolated environment for running code while maintaining security through containerization.

Python sandboxes for llms

install all mcp server in sandbox for remote usage

A Model Context Protocol (MCP) server that enables LLMs to run ANY code safely in isolated Docker containers.

Turn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.

Allow LLMs to run ANY code/configuration safely in isolated Docker containers using the Model Context Protocol (MCP).

Project for StreamableHttp MCP server sandbox

Run code in secure remote sandboxes

The @runno/mcp server provides a run_code tool that AI assistants can use to execute code snippets in various programming languages. It leverages the @runno/sandbox package, which uses WebAssembly to create isolated environments for code execution. The result of the code execution is provided over STDIO.

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

These tools are used to query sample-related information within the foundational network data set. Currently, this includes access to sandbox analysis data.

A Model Context Protocol (MCP) server for interacting with Joe Sandbox Cloud. This server exposes rich analysis and IOC extraction capabilities from Joe Sandbox and integrates cleanly into any MCP-compatible application (e.g. Claude Desktop, Glama, or custom LLM agents).

MCP Sandbox transforms JavaScript modules into secure MCP servers, enabling AI systems to access functions safely. With automatic reflection and type inference, it simplifies the integration process for developers. 🛠️💻

# 🐢🚀 Node.js Sandbox MCP ServerThis repository hosts a Node.js server that implements the Model Context Protocol (MCP) for running JavaScript in isolated Docker containers. It allows for on-the-fly npm dependency installation, making it easy to execute code safely and efficiently.

114 JSON-first system commands for AI agents. Zero dependencies, sandbox safety, MCP native. cat, ls, rm, find, grep — all output structured JSON. Glama 92%, all tools A-grade TDQS.

Lightning-paid tool stack for autonomous agents. Capital-scale-aware second-opinion /review (Sentinel mode auto-injects live trading state for trading-artifact verdicts), strategic reasoning, structured decisions, sandboxed code execution with audit proofs, paid agent-to-agent message bus, persistent memory, and a Lightning marketplace with seller payouts. Built and used daily by our own agent fleet — Warden, Sentinel, Coder, Treasury, Earner, viperclaw1 — who pay each other in sats. External agents get the same infrastructure on the same terms. Tools: - /review — Independent verdict (approve / approve_with_concerns / reject) with ranked issues + suggested fixes; Sentinel mode for capital-scale-aware trading review (~200 sats + length bonus) - /reason — Strategic analysis (~100 sats) - /decision — Structured decision with confidence + risk_level (~180 sats) - /execute — Docker-isolated Python jobs with audit hashes (Tier 1 ~700 sats) - /browse — Restricted public fetch + Playwright screenshot worker (~500 sats) - /messages/post — Paid agent-to-agent bus, 5% platform cut (~200 sats) - /memory/store + /get + /list — Cross-session persistent agent memory (~2 sats/KB)

Bridge Town is an MCP-first platform for building financial models as code. Connect any agent: Claude.ai, Codex, Opencode, Cursor. Agents can create financial models, edit files, run sandboxed forecasts, query data, work with Google Sheets, manage versions, collaborate, and publish outputs through a hosted Streamable HTTP MCP server.

Postal mail API for AI agents. Send letters, certified mail, postcards, and documents from code via MCP, with sandbox keys, webhooks, tracking, proof, and inbound mail context from a business address, PO box, office, home address, or virtual mailbox.

Postal mail API for AI agents. Send letters, certified mail, postcards, and documents from code via MCP, with sandbox keys, webhooks, tracking, proof, and inbound mail context from a business address, PO box, office, home address, or virtual mailbox.

A local encrypted execution layer for AI agents. Provides sealed scripts, protected subprocess execution, and secure local storage.

Free hosted MCP dad-jokes server used as a low-friction connectivity check before trying MCP Keeper's paid tools.