広告掲載
MCP.so
ログイン

Action MCP Example

@seuros

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

seuros

Action MCP Example について

A minimal Rails API template for creating MCP (Model Context Protocol) servers with robust tool execution capabilities and examples.

#agents#rails-api#claude#mcp-server

Action MCP Example の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp_rails_template": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "--url",
        "http://localhost:8080/mcp"
      ]
    }
  }
}

Action MCP Example のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Action MCP Example 🚀?

A simple Ruby on Rails application demonstrating how to integrate and use the ActionMCP gem. It is intended for developers who want to see how to define MCP components (prompts, resource templates, tools) within a Rails project.

How to use Action MCP Example 🚀?

Clone the repository, run bin/setup, copy .env.example to .env and fill in required values (e.g., API keys). Set up PostgreSQL (e.g., via make up for Docker on port 5466), then start the Rails server with bin/rails s. The ActionMCP server runs on port 62770, proxied by Nginx at /mcp. You can test interactively using the MCP Inspector: npx @modelcontextprotocol/inspector --url http://localhost:8080/mcp.

Key features of Action MCP Example 🚀

  • JWT‑based authentication with predefined test users
  • Adventure story prompt generator
  • Gemfile dependency resource template (JSON over gemfile://{environment})
  • Weather forecast tool via Open‑Meteo API
  • RuboCop style analysis tool for Ruby snippets
  • Dependency info tool (production, test, runtime)
  • Ruby code static analysis tool (classes, modules, methods)

Use cases of Action MCP Example 🚀

  • Generate a short narrative adventure story from a hero name and genre
  • Fetch weather data for given latitude/longitude coordinates
  • Analyze a Ruby code snippet for style offenses using RuboCop
  • Retrieve project dependencies (Gemfile) as structured JSON
  • Index and query Ruby source files for classes, modules, and methods

よくある質問

1

What are the runtime requirements?

Ruby (see `.ruby-version`) and PostgreSQL (or Docker for a temporary instance). The ActionMCP gem is sourced from [https://github.com/seuros/mcp](https://github.com/seuros/mcp).

2

How does authentication work?

JWT tokens are used. Test users (e.g., `test@example.com` / `password123`) are loaded from fixtures. Tokens can be generated in the Rails console. A pre‑configured `.mcp.json` file with a long‑lived token is provided.

3

Where does the MCP server run?

The ActionMCP server runs as a standalone server on port `62770` (via `mcp.ru`). Nginx proxies `/mcp` requests to this server.

4

What MCP components are included?

**Prompts**: `epic_adventure_prompt.rb`. **Resource Templates**: `gemfile_template.rb`. **Tools**: `dependency_info_tool.rb`, `fetch_weather_by_location_tool.rb`, `rubocop_tool.rb`, `ruby_code_analyzer_tool.rb`.

5

How can I test the MCP server interactively?

Use the MCP Inspector: `npx @modelcontextprotocol/inspector --url http://localhost:8080/mcp`. Make sure Docker is running (`docker compose up`) before executing the inspector command.

コメント

「開発者ツール」の他のコンテンツ

Heard

Heard

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.

Meticulous

Meticulous

CircleCI MCP Server

CircleCI

Manage CI/CD pipelines, debug failed builds, and optimize test suites directly from your AI agents - no terminal required. The CircleCI MCP Server is a remote server hosted by CircleCI that connects AI tools and agents

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

1

Routebase

Routebase

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

広告掲載