Ecosystem
Power up your AI apps with MCP integration, structured outputs, and community tools.
Table of contents
RubyLLM::MCP
Model Context Protocol Support for Ruby
RubyLLM::MCP brings the Model Context Protocol to Ruby, enabling your applications to connect to MCP servers and use their tools, resources, and prompts as part of LLM conversations.
What is MCP?
The Model Context Protocol is an open standard that allows AI applications to integrate with external data sources and tools. MCP servers can expose:
- Tools: Functions that LLMs can call to perform actions
- Resources: Structured data that can be included in conversations
- Prompts: Predefined prompt templates with parameters
Key Features
- π Multiple transport types (HTTP streaming, STDIO, SSE)
- π οΈ Automatic tool integration with RubyLLM
- π Resource management for files and data
- π― Prompt templates with arguments
- π Support for multiple simultaneous MCP connections
Installation
gem install ruby_llm-mcp
For detailed documentation, examples, and usage guides, visit the RubyLLM::MCP documentation.
RubyLLM::Schema
Ruby DSL for JSON Schema Creation
RubyLLM::Schema provides a clean, Rails-inspired DSL for creating JSON schemas. Itβs designed specifically for defining structured data schemas for LLM function calling and structured outputs.
Why Use RubyLLM::Schema?
When working with LLMs, you often need to define precise data structures for:
- Structured output formats
- Function parameter schemas
- Data validation schemas
- API response formats
RubyLLM::Schema makes this easy with a familiar Ruby syntax.
Key Features
- π Rails-inspired DSL for intuitive schema creation
- π― Full JSON Schema compatibility
- π§ Support for all primitive types, objects, and arrays
- π Union types with
any_of
- π¦ Schema definitions and references for reusability
Installation
gem install ruby_llm-schema
For detailed documentation and examples, visit the RubyLLM::Schema repository.
Community Projects
The RubyLLM ecosystem is growing! If youβve built a library or tool that extends RubyLLM, weβd love to hear about it. Consider:
- Opening a PR to add your project to this page
- Sharing it in our GitHub Discussions
- Using the
ruby_llm
topic on your GitHub repository
Together, weβre building a comprehensive ecosystem for LLM-powered Ruby applications.