mcp-sandbox
If you are the rightful owner of mcp-sandbox and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcpreview.com.
Python MCP Sandbox is an interactive tool for executing Python code in isolated Docker containers, allowing safe code execution and package management.
The Python MCP Sandbox is a robust platform designed to facilitate the secure execution of Python code within isolated Docker containers. This tool is particularly useful for developers and LLMs who need to run Python scripts and manage packages without risking the integrity of their primary environment. By leveraging Docker's containerization capabilities, the MCP Sandbox ensures that each code execution is isolated, preventing any potential interference or security risks. The platform also supports package management, allowing users to install and manage Python packages seamlessly. Additionally, it provides features for file generation and access, making it a comprehensive solution for Python code execution and management.
Features
- Docker Isolation: Securely run Python code in isolated Docker containers.
- Package Management: Easily install and manage Python packages.
- File Generation: Support for generating files and accessing them via web links.
Tools
- create_sandbox: Creates a new Python Docker sandbox and returns its ID for subsequent code execution and package installation.
- list_sandboxes: Lists all existing sandboxes (Docker containers) for reuse.
- execute_python_code: Executes Python code in a specified Docker sandbox.
- install_package_in_sandbox: Installs Python packages in a specified Docker sandbox.
- check_package_installation_status: Checks if a package is installed or installation status in a Docker sandbox.
- execute_terminal_command: Executes a terminal command in the specified Docker sandbox.
- upload_file_to_sandbox: Uploads a local file to the specified Docker sandbox.