Pecorino
About
A Model Context Protocol (MCP) server for deep Git history statistics, repository health tracking, and Object-Oriented Design (OOD) metrics analysis.
Details
- Author
- pecorino-mcp
- Downloads
- 173
Jump to
- 🔌 Model Context Protocol (MCP): Exposes 3 unified tools (browse, metrics, update_index) to your AI assistant
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Linux: ~/.config/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
- Parameters
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
PecorinoCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
The README includes setup instructions such as python pecorino.py /path/to/repo /path/to/output_dir.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"pecorino": {
"pecorino": {
"command": "python3",
"args": [
"-m",
"venv",
".venv"
]
}
}
}
}McpServers
{
"pecorino": {
"command": "python3",
"args": [
"-m",
"venv",
".venv"
]
}
}Pecorino MCP Server
A Model Context Protocol (MCP) server for deep Git history statistics, repository health tracking, and Object-Oriented Design (OOD) metrics analysis.
Pecorino allows Large Language Models (LLMs) and dev tools (such as Claude Desktop or Cursor) to inspect codebases, analyze code structures, compute complexity/maintainability indexes, and detect risk hotspots.
---
✨ Features
- 🔌 Model Context Protocol (MCP): Exposes 3 unified tools (browse, metrics, update_index) to your AI assistant.
- 📊 Git History Analytics: Commits, LOC growth, author contributions, activity patterns, and team performance tracking.
- 📐 Object-Oriented Design Metrics: Afferent/efferent coupling (Ca/Ce), instability (I), abstractness (A), and Distance-from-Main-Sequence (D) analysis.
- 🚨 Risk Hotspot Detection: Combines code churn (revision frequency) and complexity to pinpoint high-risk source files.
- 🗄️ Fast DuckDB-backed AST Indexing: Leverages tree-sitter to index class definitions, functions, and imports for rapid codebase navigation and search.
- 💻 Flexible CLI & HTTP SSE: Run as a standard CLI tool, start a local stdio MCP server, or deploy as a network-accessible SSE server.
---
🚀 Quick Start
1. Installation
Clone the repository recursively (to fetch the MCP SDK submodule) and set up the environment:```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
