Built by reinteractive, the world's oldest dedicated Rails agency

Turn Rails apps into LLM-ready data.

A Rails-aware codebase indexer running as an MCP server. It builds a complete relationship graph of your application, giving AI agents deep structural understanding without blowing up your token budget.

$ npx @reinteractive/rails-insight
Read the Docs
Supports Rails 6.0 up to 8.1+ • Zero file reads for structural classification. • Indexes large codebases in under 5s.

Open Beta Testing

RailsInsight is currently in open beta. If you encounter any edge cases or bugs, please raise an issue on GitHub and our team will resolve it promptly.

~/projects/my-rails-app
$ npx @reinteractive/rails-insight
Starting RailsInsight MCP Server...
[Context Loader] Loaded CLAUDE.md conventions
[Version Detector] Rails 8.0.1, Ruby 3.3.0, PostgreSQL
[Structural Scanner] Classified 1,245 files across 56 categories in 0.8s
[Graph Builder] Constructed weighted relationship graph (22 edge types)
[Done] Full index built in 4.1s — 1,245 files ready.
RailsInsight MCP Server is listening on stdio
Agent connected. Waiting for requests...
Agent Request (Claude)
Use tool get_model with args: {"name": "User"}
Schema Found
42 Tables Indexed
Graph Built
Token Budget Intact

Easily connect with your AI Agents

Claude Desktop
Cursor
VS Code
Quick Config

Integrate in seconds via MCP.

Connect any MCP-compatible client to your Rails application. The server automatically uses the workspace directory as the project root.

  • Zero Configuration

    Runs locally over stdio. No API keys, no cloud syncing.

  • Context Aware

    Automatically parses CLAUDE.md for declared conventions.

{
  "servers": {
    "railsinsight": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@reinteractive/rails-insight"]
    }
  }
}
                        
The Secret Sauce

Powered by Convention over Configuration.

Generic AI coding tools treat your Ruby files as plain, disconnected text. They waste token limits reading things they don't understand, missing the underlying architecture.

Because Rails relies on strict, predictable conventions, RailsInsight instantly maps your entire application into a complete relationship graph. It inherently knows that a route maps to a controller, which calls a model, which reads from a database table—connecting the dots for your AI agent before it even asks.

  • Builds a directed weighted graph with 22 edge types
  • Infers dependencies without reading every single file line
config/routes.rb
resources :users
app/controllers/users_controller.rb
def show; @user = User.find(params[:id])
app/models/user.rb
has_many :posts, through: :authorships
Change Detected
app/models/user.rb
.../users_controller.rb
Critical
.../process_user_data_job.rb
High
.../user_mailer.rb
Medium
Context Scoping

Know your Blast Radius.

When an AI agent modifies a core model, does it know which background jobs, mailers, or API endpoints it just broke? Usually not, unless it consumes your entire codebase budget in one go.

The Blast Radius tool leverages the relationship graph to calculate the exact structural impact of any file change. It returns a risk-ranked list of dependent files, enabling your agent to proactively review downstream effects and prevent regressions.

MCP Tool
get_blast_radius
Core Technology

Built from the ground up to understand Rails.

Generic tools treat Ruby files as plain text. RailsInsight understands conventions, building a directed graph of your entire architecture.

56 Categories Detected

Pure path-based analysis classifies every file instantly. From Models and Controllers to Solid Queue Jobs, ActionCable, and Feature Flags—with zero file reads.

Deep Extraction

19 specialized extractors parse file content to map out has_many :through, before_action filters, Devise modules, Pundit policies, and schema structures.

Token Budget Aware

Exposes your app through precise MCP tools. Your agent gets the exact architectural context it needs (e.g. blast radius) without consuming your entire context window.

Under 5 Seconds for a Large Codebase

RailsInsight completes its full index—scanning, classifying, extracting, and building the relationship graph—in under 5 seconds, even for large production Rails apps. Your AI agent starts with full structural context from the very first request, with zero warm-up wait.

<5s full index
any codebase

17 purpose-built MCP Tools.

Everything an AI agent needs to navigate your application safely.

View all tools
get_overview

Project Summary

Returns Rails/Ruby versions, database, auth strategy, key models, controllers, frontend stack, and file counts. Call this first.

get_model

Deep Model Extraction

Pulls associations, validations, scopes with queries, enums, callbacks, public methods, and database columns for a specific model.

get_blast_radius

Impact Analysis

Analyzes the impact of code changes. Returns impacted entities classified by risk level (CRITICAL/HIGH/MEDIUM/LOW) via the relationship graph.

get_coverage_gaps

Test Intelligence

Prioritized list of files needing test coverage, with structural context and per-method coverage data from SimpleCov.

get_schema

Database Schema

Extracts database schema with tables, columns, indexes, foreign keys, and complete model-to-table mapping.

12 more tools available View all

Ready to empower your AI?

RailsInsight is open source and runs entirely locally. Install it globally or run via npx directly in your Rails root.

$ npx @reinteractive/rails-insight

Get in touch with reinteractive

Have a question, need Rails expertise, or want to discuss how RailsInsight fits your team? We'd love to hear from you.

inquiries@reinteractive.com