tidewave-ai/tidewave_rails

What it solves

Tidewave Rails provides a bridge between coding agents and a running Ruby on Rails application. It solves the problem of agents being unable to interact with the live runtime state of an app, allowing them to move beyond static code analysis to actually execute code, query databases, and access real-time logs during development.

How it works

It operates as a Model Context Protocol (MCP) server that integrates directly into a Rails app via a gem. Once installed, it exposes a set of tools that an AI agent (integrated with an MCP-compatible editor or client) can call to interact with the running application process.

Who it’s for

Developers using Ruby on Rails who use AI coding agents (like Claude Code, Cursor, or VS Code) to build and debug their applications.

Highlights

• Runtime Code Execution: Acts as a Rails console for agents, allowing them to evaluate Ruby code within the app's live context.
• Database Access: Enables agents to run SQL queries against the development database to verify data or insert test records.
• Version-Specific Documentation: Retrieves documentation for classes and methods based on the exact gem versions locked in the project's Gemfile.lock.
• Source Location Resolution: Finds the exact file and line of a definition, including those generated via metaprogramming or located within gem dependencies.