✅ COMPREHENSIVE SAFETY FRAMEWORK: • Package-level safety notices with SACRED TRUST language • Server-level LLM safety protocols with specific refusal scenarios • Class-level safety reminders for AI assistants • Tool-level destructive operation warnings (🔴 DESTRUCTIVE markers) • Visual safety system: 🔴🛡️🚨 markers throughout codebase • Emergency logging infrastructure with proper escalation • Default-safe operations (dry_run=True for destructive tools) 🔒 DESTRUCTIVE OPERATION PROTECTIONS: • bulk_rename: LLM safety instructions + dry_run default • search_and_replace_batch: Comprehensive safety warnings • All destructive tools require preview before execution • Clear REFUSE scenarios for AI assistants 📚 COMPREHENSIVE DOCUMENTATION: • SACRED_TRUST_SAFETY.md: Complete safety philosophy & implementation guide • IMPLEMENTATION_COMPLETE.md: Project completion status • EMERGENCY_LOGGING_COMPLETE.md: Logging infrastructure details • UV_BUILD_GUIDE.md: Modern Python project setup • Multiple implementation guides and status docs 🔧 PROJECT MODERNIZATION: • Migrated from setup.py/requirements.txt to pyproject.toml + uv • Updated dependency management with uv.lock • Enhanced test suite with comprehensive coverage • Added examples and demo scripts ✅ VALIDATION COMPLETE: All SACRED_TRUST_SAFETY.md requirements implemented 🎯 Sacred Trust Status: PROTECTED 🚨 User Safety: PARAMOUNT 🔐 System Integrity: PRESERVED The human trusts AI assistants to be guardians of their system and data. This framework ensures that trust is honored through comprehensive safety measures.
4.7 KiB
4.7 KiB
Building Enhanced MCP Tools with uv
🚀 Quick Start with uv (Tested ✅)
Prerequisites
# Ensure uv is installed
uv --version # Should show uv 0.7.x or later
1. Clean Build (Recommended)
cd /home/rpm/claude/enhanced-mcp-tools
# Clean any previous builds
rm -rf dist/ build/ *.egg-info/
# Build both wheel and source distribution
uv build
# Verify build artifacts
ls -la dist/
# Should show:
# enhanced_mcp_tools-1.0.0-py3-none-any.whl
# enhanced_mcp_tools-1.0.0.tar.gz
2. Test Installation (Verified ✅)
# Create clean test environment
uv venv test-env
source test-env/bin/activate
# Install from built wheel
uv pip install dist/enhanced_mcp_tools-1.0.0-py3-none-any.whl
# Test core functionality
python -c "from enhanced_mcp import create_server; print('✅ Core works')"
# Install with enhanced features
uv pip install "enhanced-mcp-tools[enhanced]" --find-links dist/
# Verify enhanced-mcp command is available
enhanced-mcp --help
3. Development Installation
# Install in development mode with all features
uv pip install -e ".[dev]"
# Run validation
python test_package_structure.py
🔧 Development Workflow with uv
Create Development Environment
# Create and activate virtual environment
uv venv enhanced-mcp-dev
source enhanced-mcp-dev/bin/activate
# Install in development mode with all dependencies
uv pip install -e ".[dev]"
# Run tests
pytest
# Run linting
ruff check .
black --check .
Dependency Management
# Add a new dependency
uv add "new-package>=1.0.0"
# Add a development dependency
uv add --dev "new-dev-tool>=2.0.0"
# Update dependencies
uv pip install --upgrade -e ".[dev]"
# Show dependency tree
uv pip list --tree
📦 Distribution Building
Build All Distributions
# Clean previous builds
rm -rf dist/ build/ *.egg-info/
# Build both wheel and source distribution
uv build
# Check what was built
ls -la dist/
Build Specific Formats
# Only wheel (faster, recommended for most uses)
uv build --wheel
# Only source distribution (for PyPI)
uv build --sdist
# Build with specific Python version
uv build --python 3.11
🧪 Testing the Built Package
Test Installation from Wheel
# Create clean test environment
uv venv test-env
source test-env/bin/activate
# Install from built wheel
uv pip install dist/enhanced_mcp_tools-1.0.0-py3-none-any.whl
# Test core functionality
python -c "from enhanced_mcp import create_server; print('✅ Core import works')"
# Test enhanced features (if dependencies available)
python -c "
try:
from enhanced_mcp.sneller_analytics import SnellerAnalytics
print('✅ Enhanced features available')
except Exception as e:
print(f'⚠️ Enhanced features: {e}')
"
Run Package Validation
# Run our validation script
python test_package_structure.py
🌐 Publishing (Optional)
Test on TestPyPI
# Build first
uv build
# Upload to TestPyPI (requires account and API token)
uvx twine upload --repository testpypi dist/*
# Test installation from TestPyPI
uv pip install --index-url https://test.pypi.org/simple/ enhanced-mcp-tools
Publish to PyPI
# Upload to PyPI (requires account and API token)
uvx twine upload dist/*
# Install from PyPI
uv pip install enhanced-mcp-tools
⚡ uv Advantages for This Project
Speed Benefits
- 🚀 10-100x faster than pip for dependency resolution
- ⚡ Parallel downloads and installations
- 🗜️ Efficient caching of packages and metadata
Perfect for Optional Dependencies
# uv handles optional dependencies elegantly
uv pip install enhanced-mcp-tools[enhanced] # Fast resolution
uv pip install enhanced-mcp-tools[full] # All features
uv pip install enhanced-mcp-tools[dev] # Development
Development Workflow
# Hot reload during development
uv pip install -e . && python -m enhanced_mcp.mcp_server
🛠️ Common Commands Summary
# Setup
uv venv .venv && source .venv/bin/activate
# Install for development
uv pip install -e ".[dev]"
# Build package
uv build
# Test installation
uv pip install dist/*.whl
# Run tests
pytest
# Format code
black .
ruff check --fix .
# Clean build
rm -rf dist/ build/ *.egg-info/
🔍 Troubleshooting
Check uv Version
uv --version
Verify pyproject.toml
# uv can validate your pyproject.toml
uv pip compile pyproject.toml --dry-run
Debug Dependency Resolution
# See what uv resolves
uv pip install -e ".[full]" --dry-run -v
Build with Verbose Output
uv build -v
This workflow gives you the fastest possible build and dependency management experience! 🚀