Skip to main content
Glama
704,826 tools. Updated 2026-10-26 10:41

"A sandbox environment for running REPL code" matching MCP tools:

  • Execute approved shell commands as root in an existing Lizard sandbox; cancellation, timeout, or request failure deletes the sandbox and files, while a nonzero exit code preserves it.
    MIT
    Destructive
  • Generate sandbox-safe code examples in cURL, Node.js, or Python for SignalEDI REST operations. Uses environment placeholders and synthetic values, avoids credentials, and sets outbound to SANDBOX.
    MIT
  • Restart the idle sleep countdown for a running sandbox, keeping it awake for another full timeout; it will not wake a sleeping sandbox.
    AGPL 3.0
  • Wakes an asleep or deep-sleeping sandbox; if the owner reaches running-sandbox or server limits, optionally specify another sandbox to put to sleep first.
    AGPL 3.0
  • Run shell commands in a sandbox to safely execute AI-generated code and retrieve stdout, stderr, and exit code.
    Apache 2.0

Matching MCP Servers

Matching MCP Connectors

  • UK river levels and rainfall, bathing waters, flood warnings, weather, earthquakes and the GB…

  • Agentic Commerce Protocol sandbox: agent builds a cart, human approves a real PayPal payment.

  • Create a secure sandbox environment to run AI-generated code in isolated microVMs. Returns a sandbox ID for managing the sandbox lifecycle.
    Apache 2.0
  • Run code in a secure, isolated sandbox across multiple languages, install libraries, and capture generated visualizations for safe execution of LLM-generated code.
    MIT
  • Evaluate Julia code in a persistent REPL session. State is preserved across calls, reducing startup costs and keeping variables alive.
    MIT
  • Copy files from your local system to a Modal sandbox environment for uploading inputs, transferring configurations, or deploying code to isolated cloud-based Python environments.
    MIT
  • Show or switch the active E*TRADE environment (sandbox or production). Separate credentials avoid mixing, and production gives real data while sandbox returns canned results.
    Apache 2.0
  • Destroy the current sandbox and create a fresh one, with optional workspace wipe and named sandbox selection.
    MIT
  • Execute Python code within a project's virtual environment to access its installed dependencies. Each call runs in a fresh interpreter subprocess, ensuring isolation.
    MIT
  • Stop a running sandbox. Optionally use force to kill with SIGKILL instead of graceful SIGTERM.
    Apache 2.0
    Destructive
  • Execute shell commands within a REPL environment, returning structured output with exit code and stdout. Supports stdin piping, timeout, and custom environment variables.
    MIT
  • Query AI with model selection, sandbox code execution, and structured edit mode for code modifications.
    MIT
    Destructive
  • Boot a stopped environment and wait until SSH responds. Does nothing if already running; errors if the environment is missing.
    Apache 2.0