Skip to main content
Glama
Python MCP Sandbox Tool

Python MCP Sandbox Tool

by jonasslv

Python MCP Sandbox Tool

This tool provides a secure sandbox environment for executing Python scripts via the MCP (Model Communication Protocol). It runs scripts in isolated Docker containers with security constraints.

Features

  • Secure Sandboxing: Runs Python scripts in isolated Docker containers

  • Resource Limits:

    • Memory limit: 4096MB

    • CPU Cores: 4

    • Timeout: 120 seconds

  • Package Allowlist: Only some curated packages are allowed

  • Read-Only Filesystem: Container filesystem is read-only

  • Artifact Support: Returns artifacts created during execution

Related MCP server: py-sandbox

Usage

The tool expects a JSON request with a script field containing the Python code to execute.

Example request:

{
  "script": "print('Hello from sandbox!')\nprint('This is a test script')"
}

Installation

pip install -r requirements.txt

Running

python mcp_sandbox_tool.py

Response Format

The tool returns a JSON response with:

  • status: "success" or "error"

  • stdout: Standard output from the script

  • stderr: Standard error from the script

  • return_code: Exit code of the script

  • artifacts: Files created during execution (if any)

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables code execution in isolated Docker containers with persistent IPython, Node.js, or R kernels, supporting file import/export and cross-session transfers via MCP tools.
      6
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to execute arbitrary Python code securely in a sandboxed environment with resource limits and security constraints via MCP protocol.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Run Python, JavaScript, or shell snippets in secure, resource-limited Docker containers with no network access, exposed as MCP tools.
      2
      Apache 2.0