mcp_on_ruby 0.2.0 → 1.0.0

data/README.md

@@ -1,522 +1,240 @@
+# MCP on Ruby
+
 <div align="center">
 
-# MCP on Ruby
 [![Gem Version](https://badge.fury.io/rb/mcp_on_ruby.svg)](https://badge.fury.io/rb/mcp_on_ruby)
-[![Build](https://github.com/nagstler/ruby_mcp/actions/workflows/build.yml/badge.svg)](https://github.com/nagstler/ruby_mcp/actions/workflows/build.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![RuboCop](https://github.com/nagstler/ruby_mcp/actions/workflows/rubocop.yml/badge.svg)](https://github.com/nagstler/ruby_mcp/actions/workflows/rubocop.yml)
-[![Test](https://github.com/nagstler/ruby_mcp/actions/workflows/test.yml/badge.svg)](https://github.com/nagstler/ruby_mcp/actions/workflows/test.yml)
-[![codecov](https://codecov.io/github/nagstler/ruby_mcp/graph/badge.svg?token=SG4EJEIHW3)](https://codecov.io/github/nagstler/ruby_mcp)
-
-<strong>The Ruby way to build MCP servers and clients.</strong>
-</div>
-
-## 🔍 Introduction
-
-The [Model Context Protocol](https://modelcontextprotocol.io) provides a standardized way for applications to interact with language models. Similar to how REST standardized web APIs, MCP creates a consistent interface for working with providers like OpenAI and Anthropic.
+[![Ruby Version](https://img.shields.io/badge/Ruby-2.7%2B-red.svg)](https://www.ruby-lang.org/)
 
-![System Component Flow (Horizontal)](https://github.com/user-attachments/assets/085ad9b8-bee0-4d60-a4b7-ecf02d07f53c)
+**Model Context Protocol (MCP) server for Rails applications**
 
-> 📌 If you find this useful, **give it a ⭐ on GitHub**
+Expose your Rails app as an AI accessible interface — define tools and resources the Rails way.
 
-## 📋 Table of Contents
+[Documentation](https://rubydoc.info/gems/mcp_on_ruby) | [Contributing](#contributing)
 
-- [🔍 Introduction](#-introduction)
-- [🌟 Why MCP on Ruby?](#-why-mcp-on-ruby)
-- [📦 Installation](#-installation)
-- [🚀 Quick Start](#-quick-start)
-  - [🎮 Interactive Demo](#-interactive-demo)
-- [⚙️ Configuration Options](#️-configuration-options)
-- [🛣️ Server Endpoints](#️-server-endpoints)
-- [📚 Detailed Usage](#-detailed-usage)
-  - [Creating a Context](#creating-a-context)
-  - [Adding a Message](#adding-a-message)
-  - [Generating a Response](#generating-a-response)
-  - [Streaming a Response](#streaming-a-response)
-  - [Uploading Content](#uploading-content)
-  - [Using Tool Calls](#using-tool-calls)
-- [🚄 Rails Integration](#-rails-integration)
-- [💾 Custom Storage Backend](#-storage-backends)
-- [🔒 Authentication](#-authentication)
-- [🛠️ Development](#️-development)
-- [🗺️ Roadmap](#️-roadmap)
-- [👥 Contributing](#-contributing)
-- [📄 License](#-license)
-
-## 🌟 Why MCP on Ruby?
+</div>
 
-**MCP on Ruby** provides a comprehensive implementation of the Model Context Protocol with these features:
+---
 
-- **Provider-Ready:** Pre-built adapters for OpenAI and Anthropic - just add your API key
-- **Complete Protocol Implementation:** Fully implements the MCP specification for compatibility
-- **Conversation Management:** Context handling for multi-turn conversations
-- **Flexible Storage:** Extensible storage backends
-- **Streaming Support:** Real-time response streaming for dynamic UIs
-- **File Handling:** Upload and reference files in conversations
-- **Tool Calling:** Support for LLM function calling capabilities
-- **Battle-Tested:** Comprehensive test suite ensures reliability
+## Features
 
-The library is designed to be straightforward to use while maintaining full compatibility with the MCP specification.
+🚀 **Production-Ready** - Authentication, rate limiting, error handling, security  
+🔧 **Rails Integration** - Generators, autoloading, middleware, Railtie  
+🛠️ **Tools System** - Callable functions with JSON Schema validation  
+📊 **Resources System** - Data exposure with URI templating  
+🔒 **Security** - DNS rebinding protection, CORS, token authentication  
+⚡ **Real-time** - Server Events (SSE) foundation (full implementation coming soon)  
+🎯 **Developer-Friendly** - Clean DSL, generators, testing support  
 
-## 📦 Installation
+## Installation
 
-Add this line to your application's Gemfile:
+Add to your `Gemfile`:
 
 ```ruby
 gem 'mcp_on_ruby'
 ```
 
-And then execute:
-
-```
-$ bundle install
-```
-
-Or install it yourself as:
-
-```
-$ gem install mcp_on_ruby
-```
-
-## 🚀 Quick Start
-
-Here's how to get a basic MCP server running:
-
-```ruby
-require 'ruby_mcp'
-
-# Configure RubyMCP
-RubyMCP.configure do |config|
-  config.providers = {
-    openai: { api_key: ENV['OPENAI_API_KEY'] },
-    anthropic: { api_key: ENV['ANTHROPIC_API_KEY'] }
-  }
-end
-
-# Start the MCP server
-server = RubyMCP::Server::Controller.new
-server.start
-```
-
-### 🎮 Interactive Demo
-
-The repository includes an interactive demo that walks through all the key MCP concepts:
+Then run:
 
 ```bash
-# Terminal 1: Start the server
-cd examples/simple_server
-ruby server.rb
-
-# Terminal 2: Run the client
-cd examples/simple_server
-ruby client.rb
-```
-
-This demo provides a guided tour of the MCP functionality, showing each step of creating contexts, adding messages, and generating responses with detailed explanations.
-
-## ⚙️ Configuration Options
-
-RubyMCP offers several configuration options:
-
-```ruby
-RubyMCP.configure do |config|
-  # LLM Provider configurations
-  config.providers = {
-    openai: { 
-      api_key: ENV['OPENAI_API_KEY'],
-      api_base: 'https://api.openai.com/v1' # Optional
-    },
-    anthropic: { 
-      api_key: ENV['ANTHROPIC_API_KEY'] 
-    }
-  }
-  
-  # Storage backend (:memory, :redis, :active_record, or custom)
-  config.storage = :memory
-  
-  # Server settings
-  config.server_port = 3000
-  config.server_host = "0.0.0.0"
-  
-  # Authentication settings
-  config.auth_required = false
-  config.jwt_secret = ENV['JWT_SECRET']
-  config.token_expiry = 3600 # 1 hour
-  
-  # Limits
-  config.max_contexts = 1000
-end
+bundle install
+rails generate mcp_on_ruby:install
 ```
 
-## 🛣️ Server Endpoints
-
-The MCP server provides the following RESTful endpoints:
-
-### Engines
-- `GET /engines` - List available language models
-
-### Contexts
-- `POST /contexts` - Create a new conversation context
-- `GET /contexts` - List existing contexts
-- `GET /contexts/:id` - Get details of a specific context
-- `DELETE /contexts/:id` - Delete a context
-
-### Messages
-- `POST /messages` - Add a message to a context
-
-### Generation
-- `POST /generate` - Generate a response from a language model
-- `POST /generate/stream` - Stream a response with incremental updates
-
-### Content
-- `POST /content` - Upload content (files)
-- `GET /content/:context_id/:id` - Retrieve uploaded content
-
-## 📚 Detailed Usage
+## Quick Start
 
-### Creating a Context
+### 1. Install and Configure
 
-```ruby
-# Using the HTTP API
-response = Faraday.post(
-  "http://localhost:3000/contexts",
-  {
-    messages: [
-      {
-        role: "system",
-        content: "You are a helpful assistant."
-      }
-    ],
-    metadata: {
-      user_id: "user_123",
-      conversation_name: "Technical Support"
-    }
-  }.to_json,
-  "Content-Type" => "application/json"
-)
-
-context_id = JSON.parse(response.body)["id"]
-```
-
-### Adding a Message
-
-```ruby
-Faraday.post(
-  "http://localhost:3000/messages",
-  {
-    context_id: context_id,
-    role: "user",
-    content: "What is the capital of France?"
-  }.to_json,
-  "Content-Type" => "application/json"
-)
-```
+```bash
+# Generate MCP server files
+rails generate mcp_on_ruby:install
 
-### Generating a Response
+# Create a tool
+rails generate mcp_on_ruby:tool UserManager --description "Manage application users"
 
-```ruby
-response = Faraday.post(
-  "http://localhost:3000/generate",
-  {
-    context_id: context_id,
-    engine_id: "anthropic/claude-3-sonnet-20240229",
-    max_tokens: 1000,
-    temperature: 0.7
-  }.to_json,
-  "Content-Type" => "application/json"
-)
-
-assistant_response = JSON.parse(response.body)["content"]
+# Create a resource  
+rails generate mcp_on_ruby:resource UserStats --uri "users/{id}/stats" --template
 ```
 
-### Streaming a Response
+### 2. Configure MCP Server
 
 ```ruby
-conn = Faraday.new do |f|
-  f.request :json
-  f.response :json
-  f.adapter :net_http
+# config/initializers/mcp_on_ruby.rb
+McpOnRuby.configure do |config|
+  config.authentication_required = true
+  config.authentication_token = ENV['MCP_AUTH_TOKEN']
+  config.rate_limit_per_minute = 60
+  config.allowed_origins = [/\.yourdomain\.com$/]
 end
 
-conn.post("http://localhost:3000/generate/stream") do |req|
-  req.headers["Content-Type"] = "application/json"
-  req.body = {
-    context_id: context_id,
-    engine_id: "openai/gpt-4",
-    temperature: 0.7
-  }.to_json
-  
-  req.options.on_data = Proc.new do |chunk, size, total|
-    event_data = chunk.split("data: ").last.strip
-    next if event_data.empty? || event_data == "[DONE]"
-    
-    event = JSON.parse(event_data)
-    if event["event"] == "generation.content" && event["content"]
-      print event["content"]
-    end
-  end
+Rails.application.configure do
+  config.mcp.enabled = true
+  config.mcp.auto_register_tools = true
+  config.mcp.auto_register_resources = true
 end
 ```
 
-### Uploading Content
+### 3. Create Tools
 
 ```ruby
-file_data = Base64.strict_encode64(File.read("example.pdf"))
-
-Faraday.post(
-  "http://localhost:3000/content",
-  {
-    context_id: context_id,
-    type: "file",
-    filename: "example.pdf",
-    content_type: "application/pdf",
-    file_data: file_data
-  }.to_json,
-  "Content-Type" => "application/json"
-)
-```
-
-### Using Tool Calls
-
-```ruby
-tools = [
-  {
-    type: "function",
-    function: {
-      name: "get_weather",
-      description: "Get the current weather for a location",
-      parameters: {
-        type: "object",
+# app/tools/user_manager_tool.rb
+class UserManagerTool < ApplicationTool
+  def initialize
+    super(
+      name: 'user_manager',
+      description: 'Manage application users',
+      input_schema: {
+        type: 'object',
         properties: {
-          location: {
-            type: "string",
-            description: "City and state, e.g., San Francisco, CA"
-          }
+          action: { type: 'string', enum: ['create', 'update', 'delete'] },
+          user_id: { type: 'integer' },
+          attributes: { type: 'object' }
         },
-        required: ["location"]
+        required: ['action']
       }
-    }
-  }
-]
-
-response = Faraday.post(
-  "http://localhost:3000/generate",
-  {
-    context_id: context_id,
-    engine_id: "openai/gpt-4",
-    tools: tools
-  }.to_json,
-  "Content-Type" => "application/json"
-)
-
-if response.body["tool_calls"]
-  # Handle tool calls
-  tool_calls = response.body["tool_calls"]
-  # Process tool calls and add tool response message
-end
-```
-
-## 🚄 Rails Integration
-
-For Rails applications, create an initializer at `config/initializers/ruby_mcp.rb`:
+    )
+  end
 
-```ruby
-RubyMCP.configure do |config|
-  config.providers = {
-    openai: { api_key: ENV['OPENAI_API_KEY'] },
-    anthropic: { api_key: ENV['ANTHROPIC_API_KEY'] }
-  }
-  
-  # Use memory storage in development, consider persistent storage in production
-  if Rails.env.development? || Rails.env.test?
-    config.storage = :memory
-  else
-    config.storage = :memory  # Replace with persistent option when implemented
+  protected
+
+  def execute(arguments, context)
+    case arguments['action']
+    when 'create'
+      user = User.create!(arguments['attributes'])
+      { success: true, user: user.as_json }
+    when 'update'
+      user = User.find(arguments['user_id'])
+      user.update!(arguments['attributes'])
+      { success: true, user: user.as_json }
+    else
+      { error: 'Unsupported action' }
+    end
   end
-  
-  # Enable authentication in production
-  if Rails.env.production?
-    config.auth_required = true
-    config.jwt_secret = ENV["JWT_SECRET"]
+
+  def authorize(context)
+    # Add your authorization logic
+    context[:authenticated] == true
   end
 end
 ```
 
-And mount the server in your `config/routes.rb` file:
+### 4. Create Resources
 
 ```ruby
-Rails.application.routes.draw do
-  # Mount RubyMCP at /api/mcp
-  mount_mcp_at = "/api/mcp"
-  
-  Rails.application.config.middleware.use Rack::Config do |env|
-    env["SCRIPT_NAME"] = mount_mcp_at if env["PATH_INFO"].start_with?(mount_mcp_at)
+# app/resources/user_stats_resource.rb
+class UserStatsResource < ApplicationResource
+  def initialize
+    super(
+      uri: 'users/{id}/stats',
+      name: 'User Statistics',
+      description: 'Get detailed user statistics',
+      mime_type: 'application/json'
+    )
   end
-  
-  mount RubyMCP::Server::App.new.rack_app, at: mount_mcp_at
-  
-  # Rest of your routes
-  # ...
-end
-```
-
-## 💾 Storage Backends
-
-### Redis Storage
-
-MCP on Ruby supports Redis as a persistent storage backend:
 
-1. Add the Redis gem to your Gemfile:
-   ```ruby
-   gem 'redis', '~> 5.0'
-   ```
+  protected
 
-2. Configure Redis storage:
-   ```ruby
-   RubyMCP.configure do |config|
-     config.storage = :redis
-     config.redis = {
-       url: ENV.fetch('REDIS_URL', 'redis://localhost:6379/0'),
-       namespace: "app_mcp_#{Rails.env}",
-       ttl: 86400  # 1 day in seconds
-     }
-   end
-   ```
-
-3. Access the configured client:
-   ```ruby
-   client = RubyMCP.client
-   ```
-
-For detailed integration examples, see the [[Redis Storage](https://github.com/nagstler/mcp_on_ruby/wiki/Redis-Storage)] wiki page.
-
-
-### Custom storage 
-You can implement custom storage backends by extending the base storage class:
-
-```ruby
-class RedisStorage < RubyMCP::Storage::Base
-  def initialize(options = {})
-    super
-    @redis = Redis.new(options)
-  end
-  
-  def create_context(context)
-    @redis.set("context:#{context.id}", JSON.dump(context.to_h))
-    context
-  end
-  
-  def get_context(context_id)
-    data = @redis.get("context:#{context_id}")
-    raise RubyMCP::Errors::ContextError, "Context not found: #{context_id}" unless data
+  def fetch_content(params, context)
+    user = User.find(params['id'])
     
-    hash = JSON.parse(data, symbolize_names: true)
-    
-    # Create message objects
-    messages = hash[:messages].map do |msg|
-      RubyMCP::Models::Message.new(
-        role: msg[:role],
-        content: msg[:content],
-        id: msg[:id],
-        metadata: msg[:metadata]
-      )
-    end
-    
-    # Create the context
-    RubyMCP::Models::Context.new(
-      id: hash[:id],
-      messages: messages,
-      metadata: hash[:metadata]
-    )
+    {
+      user_id: user.id,
+      statistics: {
+        posts_count: user.posts.count,
+        comments_count: user.comments.count,
+        last_login: user.last_login_at,
+        account_created: user.created_at
+      },
+      generated_at: Time.current.iso8601
+    }
   end
-  
-  # Implement other required methods...
-end
 
-# Configure RubyMCP to use your custom storage
-RubyMCP.configure do |config|
-  config.storage = RedisStorage.new(url: ENV["REDIS_URL"])
+  def authorize(context)
+    # Check if user can access this data
+    context[:authenticated] == true
+  end
 end
 ```
 
-## 🔒 Authentication
+### 5. Start Your Server
 
-To enable JWT authentication:
-
-```ruby
-RubyMCP.configure do |config|
-  config.auth_required = true
-  config.jwt_secret = ENV['JWT_SECRET']
-  config.token_expiry = 3600 # 1 hour
-end
+```bash
+rails server
+# MCP server available at http://localhost:3000/mcp
 ```
 
-Then, create and use JWT tokens:
+## Architecture
 
-```ruby
-# Generate a token
-require 'jwt'
+```
+┌─────────────────────────────────────────────────────────────┐
+│                        Rails App                            │
+├─────────────────────────────────────────────────────────────┤
+│  app/tools/          │  app/resources/                      │
+│  ├── application_tool.rb     ├── application_resource.rb    │
+│  ├── user_manager_tool.rb    ├── user_stats_resource.rb     │
+│  └── ...                     └── ...                        │
+├─────────────────────────────────────────────────────────────┤
+│                    MCP Server Core                          │
+│  ┌─────────────────┐ ┌─────────────────┐ ┌──────────────┐   │
+│  │     Tools       │ │    Resources    │ │  Transport   │   │
+│  │  - Validation   │ │  - Templating   │ │  - HTTP      │   │
+│  │  - Authorization│ │  - Authorization│ │  - SSE       │   │
+│  │  - Execution    │ │  - Content      │ │  - Security  │   │
+│  └─────────────────┘ └─────────────────┘ └──────────────┘   │
+├─────────────────────────────────────────────────────────────┤
+│                  JSON-RPC Protocol                          │
+└─────────────────────────────────────────────────────────────┘
+```
 
-payload = {
-  sub: "user_123",
-  exp: Time.now.to_i + 3600
-}
+## Examples
 
-token = JWT.encode(payload, ENV['JWT_SECRET'], 'HS256')
+Connect your Rails MCP server with different AI clients:
 
-# Use the token in requests
-conn = Faraday.new do |f|
-  f.request :json
-  f.response :json
-  f.adapter :net_http
-end
+👉 **[Claude Desktop](examples/claude/)** - Complete setup guide with bridge script
 
-conn.get("http://localhost:3000/contexts") do |req|
-  req.headers["Authorization"] = "Bearer #{token}"
-end
-```
+## Documentation
 
-## 🛠️ Development
+👉 **[Advanced Usage](docs/advanced-usage.md)** - Custom authorization, caching, manual configuration  
+👉 **[Testing Guide](docs/testing.md)** - RSpec integration and testing patterns  
+👉 **[API Reference](docs/api-reference.md)** - Complete API documentation
 
-After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
 
-### Running Tests
+## Requirements
 
-```
-bundle exec rspec
-```
+- Ruby 2.7.0 or higher
+- Rails 6.0 or higher (for full integration)
+- JSON Schema validation support
 
-### Local Development Server
+## Dependencies
 
-```
-bundle exec ruby examples/simple_server/server.rb
-```
+Production dependencies (minimal footprint):
+- `json-schema` (~> 3.0) - JSON Schema validation
+- `rack` (~> 2.2) - HTTP transport layer
+- `webrick` (~> 1.7) - HTTP server
+
+## Contributing
 
-## 🗺️ Roadmap
+1. Fork the repository
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Write tests for your changes
+4. Ensure all tests pass (`bundle exec rspec`)
+5. Commit your changes (`git commit -am 'Add some feature'`)
+6. Push to the branch (`git push origin my-new-feature`)
+7. Create a Pull Request
 
-While RubyMCP is functional for basic use cases, there are several areas planned for improvement:
+## License
 
-- [x] Redis persistent storage backend
-- [ ] ActiveRecord storage backend
-- [ ] Complete test coverage, including integration tests
-- [ ] Improved error handling and recovery strategies
-- [ ] Rate limiting for provider APIs
-- [ ] Proper tokenization for context window management
-- [ ] More robust streaming implementation
-- [ ] Additional provider integrations
+This project is licensed under the MIT License - see the [LICENSE](LICENSE.txt) file for details.
 
-:heart: Contributions in any of these areas are welcome!
+## 🙏 Acknowledgments
 
-## 👥 Contributing
+- The [Model Context Protocol](https://modelcontextprotocol.io) team at Anthropic for creating the specification
+- The Ruby on Rails community for inspiration and conventions
 
-1. Fork the repository
-2. Create your feature branch (`git checkout -b feature/my-new-feature`)
-3. Commit your changes (`git commit -am 'Add some feature'`)
-4. Push to the branch (`git push origin feature/my-new-feature`)
-5. Create a new Pull Request
+---
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/nagstler/mcp_on_ruby.
+<div align="center">
 
-## 📄 License
+Made with ❤️ for the Ruby community
 
-The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+</div>