Ruby gem MCP server for Rails projects that lets Claude inspect files, routes, models, schema, controller-view relationships, environment config, and framework guides.
Rails MCP Server can read Rails project files, routes, model definitions, database schema files, environment configuration, controller-view relationships, and downloaded guides., The `execute_ruby` tool runs constrained Ruby code with a timeout, static forbidden-pattern checks, read-only helper methods, path validation, and sensitive-file filtering., Sandbox checks reduce risk but do not make untrusted model-generated Ruby equivalent to a formally isolated runtime; keep access scoped to projects you are comfortable exposing., Do not configure broad parent folders, unrelated repositories, production secret directories, dependency caches, logs, storage folders, or private customer data as Rails project paths., HTTP mode and network binding should stay local or behind trusted access controls; avoid exposing a project-inspection server on untrusted networks.
Privacy notes
Tool calls can expose filenames, source code, routes, model associations, validations, schema details, controller actions, view names, environment settings, guide content, and project paths to the MCP client and model context., Project files can contain proprietary code, customer workflows, internal URLs, database table names, sensitive business logic, and credentials accidentally committed outside excluded patterns., The server filters common sensitive files such as `.env`, keys, credentials, secrets, SSH files, database config, storage config, logs, temp files, and ignored files, but users should still audit project contents., Configuration tools can update local MCP client settings and create project config files, so review generated configs before sharing or committing them.
Author
Mario Alberto Chavez Cardenas
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
4 prerequisites to line up before setup. Includes a review or approval gate.
0/4 ready
Install & runtime2Review & approval215 minutes
Safety & privacy surface
Safety & privacy surface
5 safety and 4 privacy notes across 4 risk areas. Review closely: credentials & tokens, permissions & scopes, network access.
4 areas
SafetyNetwork accessRails MCP Server can read Rails project files, routes, model definitions, database schema files, environment configuration, controller-view relationships, and downloaded guides.
SafetyLocal filesThe `execute_ruby` tool runs constrained Ruby code with a timeout, static forbidden-pattern checks, read-only helper methods, path validation, and sensitive-file filtering.
SafetyPermissions & scopesSandbox checks reduce risk but do not make untrusted model-generated Ruby equivalent to a formally isolated runtime; keep access scoped to projects you are comfortable exposing.
SafetyCredentials & tokensDo not configure broad parent folders, unrelated repositories, production secret directories, dependency caches, logs, storage folders, or private customer data as Rails project paths.
SafetyPermissions & scopesHTTP mode and network binding should stay local or behind trusted access controls; avoid exposing a project-inspection server on untrusted networks.
PrivacyLocal filesTool calls can expose filenames, source code, routes, model associations, validations, schema details, controller actions, view names, environment settings, guide content, and project paths to the MCP client and model context.
PrivacyCredentials & tokensProject files can contain proprietary code, customer workflows, internal URLs, database table names, sensitive business logic, and credentials accidentally committed outside excluded patterns.
PrivacyCredentials & tokensThe server filters common sensitive files such as `.env`, keys, credentials, secrets, SSH files, database config, storage config, logs, temp files, and ignored files, but users should still audit project contents.
PrivacyLocal filesConfiguration tools can update local MCP client settings and create project config files, so review generated configs before sharing or committing them.
Disclosure: MIT-licensed Ruby gem for Rails project analysis through MCP. This entry is distinct from general code-search or editor-control servers because it provides Rails-specific analyzers, guide resources, and read-only Ruby helpers for configured Rails projects.
Safety notes
Rails MCP Server can read Rails project files, routes, model definitions, database schema files, environment configuration, controller-view relationships, and downloaded guides.
The `execute_ruby` tool runs constrained Ruby code with a timeout, static forbidden-pattern checks, read-only helper methods, path validation, and sensitive-file filtering.
Sandbox checks reduce risk but do not make untrusted model-generated Ruby equivalent to a formally isolated runtime; keep access scoped to projects you are comfortable exposing.
Do not configure broad parent folders, unrelated repositories, production secret directories, dependency caches, logs, storage folders, or private customer data as Rails project paths.
HTTP mode and network binding should stay local or behind trusted access controls; avoid exposing a project-inspection server on untrusted networks.
Privacy notes
Tool calls can expose filenames, source code, routes, model associations, validations, schema details, controller actions, view names, environment settings, guide content, and project paths to the MCP client and model context.
Project files can contain proprietary code, customer workflows, internal URLs, database table names, sensitive business logic, and credentials accidentally committed outside excluded patterns.
The server filters common sensitive files such as `.env`, keys, credentials, secrets, SSH files, database config, storage config, logs, temp files, and ignored files, but users should still audit project contents.
Configuration tools can update local MCP client settings and create project config files, so review generated configs before sharing or committing them.
Prerequisites
Ruby 3.2 or newer and a working `gem` installation.
One or more approved Rails project paths configured through `rails-mcp-config`, `projects.yml`, `RAILS_MCP_PROJECT_PATH`, or single-project mode.
Review of which project files, schema data, routes, guides, and local docs should be visible to the MCP client.
Optional guide downloads for Rails, Turbo, Stimulus, Kamal, or custom documentation.
Schema details
Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
intermediate
Tool listing metadata
Disclosure
MIT-licensed Ruby gem for Rails project analysis through MCP. This entry is distinct from general code-search or editor-control servers because it provides Rails-specific analyzers, guide resources, and read-only Ruby helpers for configured Rails projects.
Rails MCP Server is a Ruby gem that gives Claude and other MCP clients a
Rails-aware way to inspect configured projects. It exposes a compact MCP tool
surface for switching projects, discovering available tools, invoking internal
analyzers, and running constrained read-only Ruby helpers inside a Rails project
context.
Use it when a coding assistant needs Rails-specific context such as routes,
Active Record models, associations, validations, database schema, controllers,
views, environment configuration, or framework guides without granting a broad
shell server.
These sources were reviewed on 2026-06-06. Prefer the live repository,
README, RubyGems metadata, license, gemspec, Ruby execution tool, path
validator, project-switching tool, and agent guide for current setup and
operating details.
Features
Configure multiple Rails projects through projects.yml or the
rails-mcp-config terminal UI.
Auto-detect a single Rails project from RAILS_MCP_PROJECT_PATH, current
working directory, or single-project mode.
Switch between configured projects with switch_project.
Discover available analyzers with search_tools.
Invoke internal analyzers through execute_tool.
Inspect project overview, files, routes, database schema, models, controller
and view relationships, and environment configuration.
Analyze Active Record associations, validations, callbacks, scopes, and model
methods.
Load Rails, Turbo, Stimulus, Kamal, or custom documentation guides.
Run constrained read-only Ruby snippets with helper methods such as
read_file, file_exists?, list_files, and project_root.
Start over stdio by default, or use HTTP/SSE mode for advanced local proxy
workflows.
Provide setup helpers for Claude Desktop and GitHub Copilot Agent workflows.
Ask Claude to summarize a Rails application's structure before editing.
Inspect routes, controllers, views, models, associations, validations, and
database schema from one MCP workflow.
Find files and read source through Rails-aware path validation.
Load framework guides while implementing Rails, Turbo, Stimulus, or Kamal
features.
Query a Rails project with constrained read-only Ruby helpers instead of
granting shell access.
Support GitHub Copilot Agent or Claude Desktop with Rails-specific project
context.
Safety and Privacy
Rails MCP Server is a local code and project-inspection tool. It can expose
source code, routes, schema details, model relationships, configuration names,
and framework docs to the MCP client. Scope it to one approved Rails project or
a small reviewed project list, and avoid adding directories that contain
secrets, logs, private customer data, dependency caches, or unrelated projects.
The execute_ruby tool is intentionally read-only and blocks common dangerous
patterns, file writes, shell execution, network access, environment reads, and
sensitive files. Treat those checks as defense in depth, not permission to run
arbitrary unreviewed code in high-risk repositories.
Duplicate Notes
Existing catalog entries cover general code indexing, repository search, and
editor-control tools. This entry covers the separate
maquina-app/rails-mcp-server Ruby gem and its Rails-specific analyzers,
project switching, guide resources, and read-only Ruby execution workflow.
Show that Rails MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/rails-mcp-server)
How it compares
Rails MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
Ruby gem MCP server for Rails projects that lets Claude inspect files, routes, models, schema, controller-view relationships, environment config, and framework guides.
MCP server for Trello boards, cards, lists, comments, checklists, attachments, labels, board activity, workspace selection, and rate-limited Trello API automation from Claude.
✓Rails MCP Server can read Rails project files, routes, model definitions, database schema files, environment configuration, controller-view relationships, and downloaded guides.
The `execute_ruby` tool runs constrained Ruby code with a timeout, static forbidden-pattern checks, read-only helper methods, path validation, and sensitive-file filtering.
Sandbox checks reduce risk but do not make untrusted model-generated Ruby equivalent to a formally isolated runtime; keep access scoped to projects you are comfortable exposing.
Do not configure broad parent folders, unrelated repositories, production secret directories, dependency caches, logs, storage folders, or private customer data as Rails project paths.
HTTP mode and network binding should stay local or behind trusted access controls; avoid exposing a project-inspection server on untrusted networks.
✓AI Game Developer can create, move, copy, modify, and delete Unity assets, scenes, GameObjects, components, scripts, packages, and generated project files.
Tools include dynamic C# script execution, C# reflection method lookup and calls, package installation/removal, Unity test execution, editor state changes, play mode control, screenshots, and profiler access.
The MCP server supports streamable HTTP and stdio; HTTP deployments should require a bearer token and stay bound to trusted interfaces.
Server variables include optional authorization and webhook settings; webhook endpoints can receive tool, prompt, resource, connection, and authorization events.
Unity runtime connections can expose compiled game state or in-game behavior to an MCP client, not just editor-only project data.
Use source control, backups, tool filtering, and explicit review before allowing destructive tools such as asset deletion, package removal, script execution, or reflection calls.
✓Memory Bank MCP can read, create, and update files inside the configured memory-bank root.
Do not point `MEMORY_BANK_ROOT` at a home directory, source repository root, cloud-sync folder, or any directory containing secrets.
Avoid auto-approving write and update tools until the expected file structure and naming rules are established.
The path validator rejects path traversal and slash-containing file/project names, but users should still keep the root directory narrow and dedicated.
Docker mode requires a bind mount for the memory bank; review the host path and container path before granting write access.
✓Trello MCP Server can create, read, update, move, archive, and delete board data depending on token permissions and requested tools.
Card, checklist, label, due-date, start-date, comment, attachment, board, list, workspace, and active-board changes can affect real team workflows.
File attachments are added from URLs; review source URLs and destination cards before allowing an agent to attach files.
Use `TRELLO_ALLOWED_WORKSPACES` to limit workspace access, especially when a token can see personal, client, or production boards.
Require confirmation before creating boards, adding attachments, deleting or archiving cards, changing due dates, moving cards between lists, or posting comments on behalf of a user.
Privacy notes
✓Tool calls can expose filenames, source code, routes, model associations, validations, schema details, controller actions, view names, environment settings, guide content, and project paths to the MCP client and model context.
Project files can contain proprietary code, customer workflows, internal URLs, database table names, sensitive business logic, and credentials accidentally committed outside excluded patterns.
The server filters common sensitive files such as `.env`, keys, credentials, secrets, SSH files, database config, storage config, logs, temp files, and ignored files, but users should still audit project contents.
Configuration tools can update local MCP client settings and create project config files, so review generated configs before sharing or committing them.
✓Tool calls may expose Unity project paths, asset names, scene hierarchy, serialized object data, scripts, logs, screenshots, profiler metrics, test output, package metadata, and runtime state.
MCP config files and Unity plugin config can contain server URLs, connection modes, bearer tokens, authorization settings, enabled tool IDs, and cloud or local endpoint details.
Optional webhooks can receive tool, prompt, resource, connection, authorization, and token-bearing request data.
Screenshots from Game View, Scene View, cameras, or isolated GameObjects may include proprietary artwork, level design, UI, debug overlays, or unreleased game content.
Generated skills and AI-client configuration files can reveal available tools, project structure, installed packages, and local workflow assumptions.
✓Memory-bank files can contain project plans, architecture notes, decisions, credentials accidentally pasted into notes, customer context, meeting details, or personal information.
Tool calls may expose project names, file names, memory contents, root-path assumptions, and update text to the MCP client and model provider.
Multi-project listing can reveal all projects stored under the memory-bank root.
Auto-approved memory tools can persist model-generated statements as project memory without human review.
Back up important memory-bank directories and review retention expectations before sharing them across clients or machines.
✓Trello API keys, tokens, board IDs, workspace IDs, card IDs, member names, labels, comments, checklists, attachments, due dates, and activity logs can be exposed to the MCP client.
Active board and workspace selections may persist locally in Trello MCP configuration.
Card descriptions, comments, attachments, and activity histories can contain private customer, roadmap, incident, or operational data.
Proxy settings, Trello credentials, and workspace allowlists should be kept out of shared MCP configs, logs, screenshots, and transcripts.
Response previews reduce some large card-description exposure, but full-card and activity tools can still return sensitive Trello content.
Prerequisites
Ruby 3.2 or newer and a working `gem` installation.
One or more approved Rails project paths configured through `rails-mcp-config`, `projects.yml`, `RAILS_MCP_PROJECT_PATH`, or single-project mode.
Review of which project files, schema data, routes, guides, and local docs should be visible to the MCP client.
Optional guide downloads for Rails, Turbo, Stimulus, Kamal, or custom documentation.
Unity project using Unity 2022.3 or newer for the current package metadata.
Unity Hub or a local Unity Editor installation.
Node.js 20.19 or newer, or Node.js 22.12 or newer, for `unity-mcp-cli`.
An MCP client such as Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, GitHub Copilot, Cline, or another supported client.
Node.js and npm available for `npx`.
A dedicated memory-bank root directory, separate from source repositories and secrets.
Project-specific subdirectories created under `MEMORY_BANK_ROOT`.
MCP client approval rules reviewed before allowing write or update operations.
Trello API key and token with access to the boards and workspaces Claude may use.
Bun-compatible published package runtime or an MCP client that can launch the packaged stdio server through npx.
Optional `TRELLO_BOARD_ID` or `TRELLO_WORKSPACE_ID` when a default board or workspace should be selected at startup.
Optional `TRELLO_ALLOWED_WORKSPACES` to constrain the token to specific approved Trello workspaces.