"National Rail" matching MCP servers:

Enables AI tools to introspect and query any Rails application's models, schema, associations, and data through read-only, token-efficient MCP tools with configurable limits and production safeguards.

Enables Rails developers to query route tables through MCP with paginated search and single-route lookup, including file and line locations for editor jumps in RubyMine.

Lets AI coding agents ask a Rails app about itself: 35 read-only tools answer from the schema, models, routes, controllers, views, jobs and conventions, over MCP or the command line, even when the app cannot boot.

Enables LLMs to explore and search Pumpkin plugin API and WIT files, extract documentation and code blocks, and scaffold new WebAssembly plugin projects for the Pumpkin Minecraft server.

An MCP server that exposes Ruby on Rails implicit dependencies like callbacks, associations, and concerns to AI coding tools.

Deterministic AST vulnerability remediation and formal verification for AI coding assistants using Microsoft Z3 SMT logic.

Privacy-first, read-only repo intelligence for AI coding agents: scans local codebases and recommends MCP servers, repos, and research without sending data to the cloud.

Enables users to compress text, extract Python code signatures, hydrate saved session state, and save checkpoints, reducing token usage when handing context between models and agents.