This project provides a Ruby gem implementing a Model Context Protocol (MCP) server for Rails applications, enabling Large Language Models (LLMs) to interact with and analyze Rails codebases. It targets developers and AI engineers seeking to integrate LLMs into their Rails development workflow for tasks like code exploration, documentation access, and configuration analysis.

How It Works

The server implements the MCP specification, allowing LLMs to request and utilize tools for interacting with Rails projects. It supports both STDIO and HTTP modes, offering JSON-RPC and Server-Sent Events (SSE) endpoints in HTTP mode. The core functionality revolves around a suite of tools that provide access to project structure, files, routes, models, database schema, controller-view relationships, and environment configurations. It also facilitates loading documentation for Rails, Turbo, Stimulus, and Kamal.

Quick Start & Requirements

• Install the gem: gem install rails-mcp-server
• Requires Ruby.
• Configuration involves editing projects.yml to list Rails project paths.
• Official documentation: https://github.com/maquina-app/rails-mcp-server

Highlighted Details

• Supports multiple Rails projects via configuration.
• Offers tools for detailed analysis of models, routes, and database schemas.
• Integrates with LLM clients like Claude Desktop.
• Provides access to official Rails, Turbo, Stimulus, and Kamal documentation.
• Includes an MCP Inspector for testing and debugging.

Maintenance & Community

• Contributions via bug reports and pull requests are welcome on GitHub.
• GitHub repository: https://github.com/maquina-app/rails-mcp-server

Licensing & Compatibility

• Released under the MIT License, permitting commercial use and modification.

Limitations & Caveats

Ruby version manager users must configure Claude Desktop to use the correct Ruby shim path to avoid startup failures. The --bind-all flag for HTTP mode should only be used on trusted networks due to increased attack surface.