Code Execution & Sandboxes MCP servers

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

A private persistent computer: files and a bash shell that survive between runs.

Containerized environments for coding agents: each agent works in its own fresh container and git branch, with execution history and terminal access.

Connect AI coding agents to MATLAB. Run code, tests, and analysis via MCP.

Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.

connects QGIS Desktop to Claude AI through the MCP. This integration enables prompt-assisted project creation, layer loading, code execution, and more.

Runtime-level MCP server for Phoenix development: run code, read logs, query the DB, read docs.

Bash for AI agents on Windows via deterministic bash-to-PowerShell translation, without WSL or a VM, with GNU-style output and persistent cwd and env.

SSH control for Linux and Windows servers: execute remote shell commands with password or SSH key authentication.

Clojure development tools, direct access to the running program via REPL.

Autonomous shell execution, computer control and coding agent for Mac.

Access iTerm: run commands and ask questions about what is shown in the terminal.

Manage multiple SSH servers: commands, file transfer and rsync, database dumps and queries, backups, health monitoring, tunnels and per-server security modes.

Runtime-level MCP server for Rails development: run code, read logs, query the DB, read docs.

Run code in secure sandboxes hosted by E2B

Run untrusted Python/JavaScript code in WebAssembly sandboxes.

Code Runner MCP Server which can run code in various programming languages.

View, edit and run ComfyUI node-based image generation workflows, with an embedded terminal.

Access any API through its existing OpenAPI documentation.

Gru-sandbox(gbox) is an open source project that provides a self-hostable sandbox for MCP integration or other AI agent usecases.

Run JavaScript snippets in isolated Docker sandboxes with on-the-fly npm dependency installation and clean teardown.

MCP server for creating, validating, and exporting Oh My Posh terminal prompt configurations.

Run shell commands securely, auditably and on demand in isolated environments such as Docker.

Live layered dependency map for bottom-up development, drawn by the agent in a terminal pane.

Enhanced Godot 4.5-4.7 MCP: headless+editor+bridge, secure GDScript sandbox, closed-loop AI dev.

Take website screenshots from the terminal, CI, or an AI agent. Local CLI and MCP server that drives your installed Chrome.

Unified execution environment for Python code, shell commands, and programmatic MCP tool calls

SSH connection manager with a TUI dashboard for discovering, searching and running commands on remote hosts.

JavaScript sandbox that uses V8 isolation to run AI-generated code locally, with heap snapshotting for persistent sessions.

Safe Python interpreter based on Hugging Face smolagents' LocalPythonExecutor.

Execute any LLM-generated code in the YepCode secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages

WASM sandbox for MCP tools. WASI-isolated, fuel/memory/I/O capped, attested.

An MCP server that lets AI agents act like a human at a real terminal, local or over SSH.

Rust reimplementation of WCGW for coding agents: shell execution and file management.

MCP server that exposes arbitrary CLI tools and shell scripts as MCP Tools via YAML configuration

MCP server that exposes arbitrary CLI tools and shell scripts as MCP Tools via YAML configuration

CLI and MCP server for termless — terminal capture, screenshots, and AI agent integration

MCP server that exposes arbitrary CLI tools and shell scripts as MCP Tools via YAML configuration

Access any API via its OpenAPI specification, with full JSON Schema support for parameters and request bodies.

Create and manage secure sandboxes for running AI agent code

Delegate tasks to other AI providers' models, e.g. ask OpenAI to generate an image.

Python runtime interpreter that executes submitted code in an isolated environment.

Manage AWS EC2, Hetzner, OVH and SSH servers: commands, logs, CloudWatch/CloudTrail queries, fleet health, IP banning and S3, with tiered safety guards.

Terminal for AI coding agents: persistent PTY sessions, incremental reads, headless screen capture, multi-agent orchestration and a web dashboard.

Verified desktop control for agents on Windows and Linux: apps with no API, windows, shell, browser.

Local macOS servers for Mail, Calendar, Reminders, Messages, Contacts, Notes, Shortcuts, Files, Maps and system tools, unified or standalone.

Submit SLURM jobs, run YAML workflows, monitor GPU resources, manage SSH profiles and sync files with local or SSH-remote HPC clusters.

Windows desktop automation with entity-based actions instead of coordinate clicks, using UIA, CDP, screenshots, keyboard, mouse, clipboard and terminal control.