MCP Python Interpreter

MCPOpen SourceNOASSERTION56.5

by yzfly • Tools & CLI

A local MCP server that lets LLM agents run Python code, manage environments, and read/write files inside an isolated working directory.

Example Use Cases

1
Execute Python code or run scripts in a controlled environment and capture stdout/stderr results.
2
Read, create, or modify project files (including binary files) within a secured, isolated working directory.
3
Inspect and manage Python environments and packages (list environments, list installed packages, install packages).

Description

This MCP server exposes Python environment and file-system capabilities to LLMs: list and use Python environments, run code or scripts, manage packages, and perform safe file read/write operations (text and binary). It enforces an isolated working directory, file size limits, and overwrite protections to reduce risk when executing code. Useful for automating development tasks, debugging, and programmatic execution from agent workflows.

Capabilities(15 total)

Tools (10)

list_python_environments

List all available Python environments (system Python and conda environments).

list_installed_packages

List installed packages for a specific Python environment. Args: environment: Name of the Python environment

environment:string

run_python_code

Execute Python code with flexible execution modes. Args: code: Python code to execute execution_mode: Execution mode - "inline" (default, fast, in-process) or "subprocess" (isolated) session_id: Session ID for inline mode to maintain state across executions environment: Python environment name (only for subprocess mode) save_as: Optional filename to save the code before execution timeout: Maximum execution time in seconds (only enforced for subprocess mode) Returns: Execution result with output Execution modes: - "inline" (default): Executes code in the current process. Fast and reliable, maintains session state. Use for most code execution tasks. - "subprocess": Executes code in a separate Python process. Use when you need environment isolation or a different Python environment.

code:string*execution_mode:stringsession_id:stringenvironment:stringsave_as:anytimeout:integer

run_python_file

Execute a Python file (always uses subprocess for file execution). Args: file_path: Path to the Python file to execute environment: Name of the Python environment to use arguments: List of command-line arguments to pass to the script timeout: Maximum execution time in seconds (default: 300)

file_path:string*environment:stringarguments:anytimeout:integer

install_package

Install a Python package in the specified environment. Args: package_name: Name of the package to install environment: Name of the Python environment upgrade: Whether to upgrade if already installed timeout: Maximum execution time in seconds

package_name:string*environment:stringupgrade:booleantimeout:integer

Prompts (3)

python_function_template

Generate a template for a Python function with docstring.

description

refactor_python_code

Help refactor Python code for better readability and performance.

code

debug_python_error

Help debug a Python error.

codeerror_message

Resources (2)

get_environments_resource

List all available Python environments as a resource.

URI: python://environmentsMIME: text/plain

get_working_directory_listing

List all Python files in the working directory as a resource.

URI: python://directoryMIME: text/plain

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

CRITICAL

Shell/code execution or full filesystem access

Trust Score

C54/100

9/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities10 Tools / 3 Prompts / 2 Resources

Owneryzfly

CategoryTools & CLI

DependenciesStandalone

Set Your Username