Auto-expose Rails app structure to AI via MCP. Zero config, 11 read-only tools.
Auto-expose Rails app structure to AI via MCP. Zero config, 11 read-only tools.
You catch it. You fix it. You re-prompt. It breaks something else.
Built by a Rails developer with 10+ years of production experience.
brakeman for security scanning, listen for watch mode, ripgrep for fast search ---Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| search_code | Trace: definition + source + callers + tests. Also: definition, call, class filters |
| get_edit_context | Method-aware code extraction with class context |
| analyze_feature | Full-stack: models + controllers + routes + services + jobs + views + tests |
| get_context | Composite: schema + model + controller + routes + views in one call |
| onboard | Narrative app walkthrough (quick/standard/full) |
| get_schema | Columns with indexed/unique/encrypted/default hints |
| get_model_details | AST-parsed associations, validations, scopes, enums, macros - each result tagged [VERIFIED] or [INFERRED] |
| get_callbacks | Callbacks in Rails execution order with source |
| get_concern | Concern methods + source + which models include it |
| get_controllers | Actions + inherited filters + render map + strong params |
| get_routes | Code-ready helpers (post_path(@record)) + required params |
| get_view | Templates with ivars, Turbo wiring, Stimulus refs, partial locals |
| get_stimulus | HTML data-attributes (dashes!) + targets + values + actions |
| get_partial_interface | What locals to pass + what methods are called on them |
brakeman for security scanning, listen for watch mode, ripgrep for fast search ---Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Shared, git-tracked working memory for AI agents that share a codebase. What one Claude / Cursor / Cline learns about your repo, the next one picks up automatically. No database. No SaaS. Just files…
Second Opinion lets installed AI coding agents use each other as opt-in subagents.
Every Level RMM endpoint, plus a local SQLite fleet store and offline cross-entity rollups no Level
A Model Context Protocol (MCP) server that connects AI assistants to the Unmarkdown API. Convert markdown to beautifully formatted documents, manage your document library, and publish pages to the…