Connect your AI assistant using the MCP protocol URI:

sse://localhost:6969/sse

The AI can now invoke the analyze_changes tool to get code quality feedback!

🧠 Analysis Dimensions

Lucidity analyzes code across 10 critical quality dimensions:

Unnecessary Complexity - Identifies overly complex algorithms, excessive abstractions, and convoluted logic
Poor Abstractions - Detects leaky or inappropriate abstractions and unclear separation of concerns
Unintended Code Deletion - Catches accidental removal of critical functionality or validation
Hallucinated Components - Finds references to non-existent functions, classes, or APIs
Style Inconsistencies - Spots deviations from project coding standards and conventions
Security Vulnerabilities - Identifies potential security issues in code changes
Performance Issues - Detects inefficient algorithms or operations that could impact performance
Code Duplication - Finds repeated logic or functionality that should be refactored
Incomplete Error Handling - Spots missing or inadequate exception handling
Test Coverage Gaps - Identifies missing tests for critical functionality

📊 Example AI Assistant Queries

With an AI assistant connected to Lucidity, try these queries:

"Analyze the code quality in my latest git changes"
"Check for security vulnerabilities in my JavaScript changes"
"Make sure my Python code follows best practices"
"Identify any performance issues in my recent code changes"
"Are there any unintended side effects in my recent refactoring?"
"Help me improve the abstractions in my code"
"Check if I've accidentally removed any important validation"
"Find any hallucinated API calls in my latest commit"
"Is my error handling complete and robust?"
"Are there any test coverage gaps in my new feature?"

🛠️ Available MCP Tools

Tools

analyze_changes - Prepares git changes for analysis through MCP
- Parameters:
  - workspace_root: The root directory of the workspace/git repository
  - path: Optional specific file path to analyze

💻 Development

Lucidity uses UV for dependency management and development workflows. UV is a fast, reliable Python package manager and resolver.

# Update dependencies
uv sync

# Run tests
pytest

# Run linting
ruff check .

# Run type checking
mypy .

🔧 Logging Behavior

Lucidity handles logging differently depending on the transport:

SSE transport: Full console logging is enabled
Stdio transport with --log-file: All logs go to the file, console is disabled
Stdio transport without --log-file: Only warnings and errors go to stderr, info logs are disabled

This ensures that stdio communication isn't broken by logs appearing on stdout.

🎛️ Command-line Options

usage: lucidity-mcp [-h] [--debug] [--host HOST] [--port PORT] [--transport {stdio,sse}]
                [--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}] [--verbose]
                [--log-file LOG_FILE]

options:
  -h, --help            show this help message and exit
  --debug               Enable debug logging
  --host HOST           Host to bind the server to (use 0.0.0.0 for all interfaces)
  --port PORT           Port to listen on for network connections
  --transport {stdio,sse}
                        Transport t

Categories

Current Category: code-quality

mcp-server-analyzer

lucidity-mcp