yoloshii/mcp-code-execution-enhanced

42 stars · Last commit 2025-11-21

Enhanced MCP code execution. Agent framework-agnostic (optimized for Claude Code). Skills framework (99.6% token reduction), multi-transport, sandboxing

README preview

# MCP Code Execution - Enhanced Edition

**99.6% Token Reduction** through CLI-based scripts and progressive tool discovery for Model Context Protocol (MCP) servers.

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
[![Claude Code](https://img.shields.io/badge/Claude_Code-Optimized-5436DA.svg)](https://docs.claude.com/en/docs/claude-code)

> **Note:** This project is optimized for [Claude Code](https://docs.claude.com/en/docs/claude-code) with native Skills support. The core runtime works with any AI agent. Scripts with CLI arguments achieve 99.6% token reduction.

---

## 🎯 What This Is

An **enhanced implementation** of Anthropic's [Code Execution with MCP](https://www.anthropic.com/engineering/code-execution-with-mcp) pattern, **optimized for Claude Code**, combining the best ideas from the MCP community and adding significant improvements:

- **Scripts with CLI Args**: Reusable Python workflows with command-line parameters (99.6% token reduction)
- **Multi-Transport**: Full support for stdio, SSE, and HTTP MCP servers
- **Container Sandboxing**: Optional rootless isolation with security controls
- **Type Safety**: Pydantic models throughout with full validation

View full repository on GitHub →