How do I use Rails Console MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Rails Console MCP Server show me the User model schema and associations" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Rails Console MCP Server

by himanshukale36

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Rails Console MCP Server

A generic Model Context Protocol (MCP) server that provides AI models (Claude Desktop, Cursor, Codex, etc.) with read-only access to any Rails application's models, database schema, and data.

Features

🔌 Works with ANY Rails app - Configure via config.json
🛡️ Read-only by default - Blocks DDL/DML operations
📊 8 powerful tools for model introspection and querying
⚡ Token efficient - Returns structured JSON, not verbose text
🔄 Hot reload - Reload Rails code without restarting
🔒 Environment-aware - Production requires explicit opt-in

Related MCP server: mcp-business-data-server

Quick Start

1. Install Dependencies

cd /home/himanshu/projects/rails-console-mcp
npm install
npm run build

2. Configure

Copy the example config and edit for your Rails app:

cp config.example.json config.json
# Edit config.json with your Rails app path

{
  "railsAppPath": "/home/himanshu/projects/Transcripto",
  "environment": "development",
  "readOnly": true,
  "maxRows": 100,
  "queryTimeoutSeconds": 30
}

3. Configure Your AI Tool

Claude Desktop (~/.claude/claude_desktop_config.json):

{
  "mcpServers": {
    "rails-console": {
      "command": "node",
      "args": ["/home/himanshu/projects/rails-console-mcp/dist/index.js"]
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "rails-console": {
      "command": "node",
      "args": ["/home/himanshu/projects/rails-console-mcp/dist/index.js"]
    }
  }
}

VS Code (.vscode/mcp.json):

{
  "servers": {
    "rails-console": {
      "type": "stdio",
      "command": "node",
      "args": ["/home/himanshu/projects/rails-console-mcp/dist/index.js"]
    }
  }
}

4. Restart Your AI Tool

Restart Claude Desktop / Cursor / VS Code to load the MCP server.

Available Tools

Tool	Description
`list_models`	List all models with summary metadata (table name, column/association counts)
`get_model_schema`	Full model definition: columns, associations, validations, scopes, enums, callbacks
`get_table_schema`	Raw database table schema (columns, indexes, FKs, PKs)
`execute_query`	Safe read-only SELECT queries with automatic LIMIT
`reload_environment`	Reload Rails code (development only)
`get_model_counts`	Row counts for models with optional WHERE clause
`search_models`	Find models by name/table pattern (regex)
`get_associations_graph`	Graph of model relationships (nodes/edges)

Architecture

┌─────────────────────┐     stdio (JSON-RPC)     ┌──────────────────────┐
│  AI Tool            │ ◄──────────────────────► │  Node.js MCP Server  │
│  (Claude, Cursor)   │                          │  @modelcontextprotocol│
└─────────────────────┘                          └──────────┬───────────┘
                                                             │
                                                    spawns Ruby sidecar
                                                             │
                                                             ▼
                                                 ┌──────────────────────┐
                                                 │  Ruby Sidecar        │
                                                 │  (loads Rails env)   │
                                                 │  - ActiveRecord      │
                                                 │  - All model metadata│
                                                 └──────────┬───────────┘
                                                            │
                                                            ▼
                                                 ┌──────────────────────┐
                                                 │  Rails App           │
                                                 │  (any path)          │
                                                 │  config.railsAppPath │
                                                 └──────────────────────┘

The Ruby sidecar loads the full Rails environment (config/environment.rb) giving access to:

All ActiveRecord models with associations, scopes, validations, callbacks, enums
Database schema via ActiveRecord::Base.connection
Safe query execution through ActiveRecord

Configuration Reference

Option	Type	Default	Description
`railsAppPath`	string	required	Absolute path to Rails app root
`environment`	string	`"development"`	Rails env to load
`readOnly`	boolean	`true`	Block DDL/DML operations
`maxRows`	number	`100`	Max rows per query
`queryTimeoutSeconds`	number	`30`	Query timeout
`allowedEnvironments`	string[]	`["development","test"]`	Allowed Rails envs
`sidecar.rubyPath`	string	`"ruby"`	Ruby executable path
`sidecar.startupTimeoutSeconds`	number	`30`	Sidecar startup timeout
`logging.level`	string	`"info"`	Log level

Security

Read-only by default - Only SELECT queries allowed
Production protection - Requires explicit allowedEnvironments config
Query validation - Blocks DDL/DML keywords
Parameterized queries - Use params array for safe interpolation
Row limits - Automatic LIMIT enforcement

Development

# Watch mode for development
npm run dev

# Run tests
npm test

# Type check
npx tsc --noEmit

Example Usage

Once configured, ask your AI tool:

"List all models in my Rails app" "Show me the schema for the Transcription model including associations" "How many transcriptions were created this week?" "Show me the association graph for User, Transcription, and Speaker" "Run a query to find all transcriptions with status 'completed'"

Requirements

Node.js 18+
Ruby 3.0+ (matching your Rails app)
Rails 6.0+ (tested with Rails 8)
Bundler installed in target Rails app

License

MIT

This server cannot be deployed

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Related MCP Connectors

QueryBearOAuth
io.github.spencerpauly
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Databases RAG Systems
2
https://mcp.querybear.com/mcp
Dataassist-IOOAuth
io.github.DataAssistIO
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Search Databases
2
https://app.dataassist.io/mcp
mcpOAuth
com.vibgrate
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Security Monitoring
2
https://mcp.vibgrate.com
Singularity - MCP Discovery & Security Gateway AOAuth
io.github.gaurav-kumar-sinha-060705
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Security Developer Tools
11
https://singularity-osd2.onrender.com/mcp

Related MCP Servers

MCP Guide Schema Query
Databases File Systems
BaoNgoThien18
A
license
Not graded
quality
D
maintenance
Enables AI tools to understand a database, inspect schema, and run safe SELECT queries with SQL guardrails, plus optional codebase reading.
Updated 4 months ago (2026-07-12 05:10 UTC)
MIT
mcp-business-data-server
Databases Security Workplace & Productivity
neoprofiAI
A
license
Not graded
quality
C
maintenance
Enables MCP clients such as Claude, ChatGPT and Cursor to answer business questions about sales, customers, orders and spreadsheets in natural language by reading live Postgres/SQLite databases and Google Sheets without exporting files or gaining write access. Guardrails include AST-based read-only SQL validation, read-only database roles, row/byte caps with pagination, PII masking, bearer-token auth for remote HTTP use, and a full JSONL audit log of every tool call.
Updated a month ago (2026-09-29 08:32 UTC)
MIT
Express REST API and MCP
Developer Tools Databases
dSchaefer97
A
license
Not graded
quality
A
maintenance
Exposes every generated CRUD service to LLM clients such as Claude, ChatGPT, or Cursor through discoverable MCP tools for create, update, and list actions plus read-only resources, so models can query and manipulate data without raw HTTP calls. It runs alongside the same codebase's REST endpoints, letting clients and AI share one data layer.
Updated 10 days ago (2026-10-20 09:22 UTC)
MIT
PgSafe MCP
Databases Security
johannschiffer
A
license
A
quality
A
maintenance
Enables AI agents to inspect database schemas and run strictly read-only SQL queries with guardrails against destructive statements, multi-statement chaining, and unbounded scans. Supports SQLite natively and PostgreSQL optionally.
Updated a day ago (2026-10-28 15:51 UTC)
4
MIT

Rails Console MCP Server

Features

Quick Start

1. Install Dependencies

2. Configure

3. Configure Your AI Tool

4. Restart Your AI Tool

Available Tools

Architecture

Configuration Reference

Security

Development

Example Usage

Requirements

License

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

MCP Guide Schema Query

mcp-business-data-server

Express REST API and MCP

PgSafe MCP