rails-ai-context

Overview

rails-ai-context is a comprehensive MCP server designed to eliminate AI guesswork when working with Ruby on Rails applications. It exposes 38 tools that allow AI assistants to query your Rails app's schema, models, routes, controllers, views, and conventions directly, rather than inferring from training data. The server uses Prism AST parsing to provide accurate information with confidence tags indicating whether data is verified or inferred. It integrates seamlessly with popular AI coding assistants like Claude Code, Cursor, GitHub Copilot, and others.

Try asking AI

After installing, here are 7 things you can ask your AI assistant:

• search_code

  Trace code definitions, sources, callers, and tests

  Try:Trace where 'publishable?' is used in the codebaseTry:Find all calls to User.create method
• get_schema

  Get table columns with indexes, uniqueness, encryption, and defaults

  Try:Show me the columns in the users tableTry:What columns exist in the orders table with their types?
• get_model_details

  Get associations, validations, scopes, enums with verification tags

  Try:Show me all associations for the User modelTry:What validations exist on the Post model?
• get_controllers

  Get controller actions, inherited filters, render maps, and strong params

  Try:Show me the actions in the UsersControllerTry:What filters are applied to PostsController#create?
• get_routes

  Get route helpers with required parameters

  Try:Show me all routes for the posts resourceTry:What helper is available for the user profile path?
• analyze_feature

  Full-stack analysis of models, controllers, routes, services, jobs, views, tests

  Try:Analyze the billing feature in the appTry:Show me everything related to user authentication
• get_view

  Get view templates with ivars, Turbo wiring, Stimulus refs, partial locals

  Try:Show me the new user registration templateTry:What partials are used in the dashboard view?
• get_test_info

  Get fixtures, relationships, and test templates matching project patterns

  Try:Show me the test fixtures for the Post modelTry:What test patterns are used in this project?
• validate

  Run syntax, semantic, and security (Brakeman) validation

  Try:Check for security issues in the appTry:Validate the recent changes for syntax errors
• diagnose

  One-call error diagnosis with classification, context, git, and logs

  Try:Diagnose why the user signup is failingTry:Analyze the production error from stack trace
• get_frontend_stack

  Get frontend framework, Hotwire, TypeScript, and package manager info

  Try:What frontend framework is being used?Try:Show me the JavaScript package dependencies
• query

  Safe read-only SQL with timeout, row limit, and column redaction

  Try:Show me the 10 most recent usersTry:Count orders by status

Comparable tools

Installation

gem "rails-ai-context", group: :development
rails generate rails_ai_context:install

gem install rails-ai-context
cd your-rails-app
rails-ai-context init     # interactive setup
rails-ai-context serve    # start MCP server

{
  "mcpServers": {
    "rails-ai-context": {
      "command": "rails",
      "args": ["ai:serve"],
      "env": {}
    }
  }
}

FAQ

What AI assistants are compatible with rails-ai-context?

It works with Claude Code, Cursor, GitHub Copilot, OpenCode, Codex CLI, and any terminal-based AI tools through its CLI mode.

How does the server provide accurate information about my Rails app?

It uses Prism AST parsing to analyze your codebase directly, providing results marked as [VERIFIED] when data is confirmed and [INFERRED] when requiring runtime checks.

Compare rails-ai-context with