gensecaihq/MCP-Developer-SubAgent

README preview

# Claude Code MCP Developer SDK

[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
[![Production Ready](https://img.shields.io/badge/Production-Ready-brightgreen.svg)](https://github.com/gensecaihq/MCP-Developer-SubAgent)
[![Security Hardened](https://img.shields.io/badge/Security-Hardened-red.svg)](https://github.com/gensecaihq/MCP-Developer-SubAgent)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Claude Code Compatible](https://img.shields.io/badge/Claude%20Code-Compatible-green.svg)](https://docs.anthropic.com/en/docs/claude-code)
[![MCP Protocol](https://img.shields.io/badge/MCP-Protocol-purple.svg)](https://modelcontextprotocol.io)
[![Anthropic Endorsed](https://img.shields.io/badge/Anthropic-Endorsed-blue.svg)](https://github.com/gensecaihq/MCP-Developer-SubAgent)
[![No Telemetry](https://img.shields.io/badge/No%20Telemetry-Privacy%20First-green.svg)](https://github.com/gensecaihq/MCP-Developer-SubAgent/blob/main/PRIVACY.md)
[![Audit Score](https://img.shields.io/badge/Audit%20Score-10%2F10-success.svg)](https://github.com/gensecaihq/MCP-Developer-SubAgent)

**Production-ready** Claude Code framework for Model Context Protocol (MCP) development with 8 specialized AI sub-agents, FastMCP integration, and **hardened enterprise-grade security hooks**. **Audit Score: 10/10** - Security-audited, fully functional across Windows, macOS, and Linux with immediate usability (no installation required for core features).

## 🚀 Features

### Dual-Mode Architecture
- **📝 Markdown-Driven Sub-Agents**: 8 specialized agents in `.claude/agents/` for Claude Code integration
- **🔧 Programmatic SDK**: Full Python SDK with async support and official Anthropic API integration
- **🎯 Hybrid Operation**: Both systems work seamlessly together with automatic fallback

View full repository on GitHub →