MCP Python Executor logo

MCP Python Executor

by bsmi021

The MCP Python Executor is a Model Context Protocol (MCP) server designed for executing Python code and managing Python packages within a controlled environment. It provides a secure and configurable way to run Python scripts and install necessary dependencies.

View on GitHub

Last updated: N/A

What is MCP Python Executor?

The MCP Python Executor is a server that allows you to execute Python code and manage Python packages. It is designed to provide a safe and controlled environment for running Python scripts, with features like resource limits and pre-configured packages.

How to use MCP Python Executor?

The server is configured through environment variables in the MCP settings. You can use the execute_python tool to run Python code either inline or from a script path. The install_packages tool allows you to install Python packages.

Key features of MCP Python Executor

  • Execute Python code with safety constraints

  • Install and manage Python packages

  • Pre-configure commonly used packages

  • Resource monitoring and limits

  • Health checks and metrics

  • Structured logging

Use cases of MCP Python Executor

  • Executing Python code snippets in a sandboxed environment

  • Running automated Python scripts as part of a larger system

  • Providing a Python execution environment for users with limited access

  • Managing Python dependencies for different projects

FAQ from MCP Python Executor

How do I specify which Python packages to pre-install?

Use the PREINSTALLED_PACKAGES environment variable to define a space-separated list of packages.

How can I limit the memory usage of a Python execution?

Set the MAX_MEMORY_MB environment variable to the desired memory limit in megabytes.

What happens if a Python execution takes too long?

The execution will be terminated after the time specified in the EXECUTION_TIMEOUT_MS environment variable.

How do I execute a Python script from a file?

Use the scriptPath parameter in the execute_python tool and provide the path to your script.

What logging levels are supported?

The supported logging levels are debug, info, and error. You can configure it with the LOG_LEVEL environment variable.