Lucidity

AI-powered code quality analysis using MCP to help AI assistants review code more effectively. Analyze git changes for complexity, security issues, and more through structured prompts.

python

79

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "hyperb1iss-lucidity-mcp": {
      "command": "lucidity-mcp",
      "args": []
    }
  }
}

Lucidity MCP Server provides structured, prompt-based analysis of code changes to help AI coding assistants produce cleaner, safer, and more maintainable code. It inspects changes, compares them against the original, and outputs actionable feedback across multiple quality dimensions to guide your review and improvements.

How to use

Start the Lucidity MCP Server in stdio mode for terminal use or in SSE mode for network access. Connect your MCP client to the server to begin analyzing your code changes. You can have Lucidity analyze your latest git changes, detect potential issues, and return concrete recommendations you can apply before committing.

Typical workflow with an MCP client:

How to install

Prerequisites you need before installing Lucidity MCP Server:

Python 3.13 or higher
Git for repository access
UV package manager for dependency management

Install and set up a virtual environment, then install dependencies using UV.

# Clone the Lucidity MCP repository
git clone https://github.com/hyperbliss/lucidity-mcp.git
cd lucidity-mcp

# Set up a virtual environment with UV
uv venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies with UV
uv sync

Run the Lucidity MCP server

Start the server in terminal (stdio) mode or enable network access with SSE.

# Start with stdio transport (for terminal use)
lucidity-mcp

# Start with SSE transport (for network use)
lucidity-mcp --transport sse --host 127.0.0.1 --port 6969

# Run with debug logging
lucidity-mcp --debug

# Run with file logging
lucidity-mcp --log-file lucidity.log

Using with AI Assistants

If you want to connect an AI assistant via the MCP protocol, run Lucidity in SSE mode and connect your assistant to the provided URI.

lucidity-mcp --transport sse

Connect your MCP client to the server using the following URI:

sse://localhost:6969/sse

The AI assistant can now invoke the analyze_changes tool to receive code quality feedback.


## Available tools

### analyze\_changes

Prepares git changes for analysis and feeds them into Lucidity so that you receive structured feedback on code quality and potential issues.