Discover and explore top open-source AI tools and projects—updated daily.
patviceRuby client for Model Context Protocol (MCP) enabling structured LLM workflows
Top 99.1% on SourcePulse
This library provides a full-featured Ruby client for the Model Context Protocol (MCP), enabling developers to build structured, composable Large Language Model (LLM) workflows directly within Ruby applications using the RubyLLM framework. It simplifies the integration of MCP-compliant tools, resources, and prompts, offering a Ruby-first API for enhanced LLM interaction and workflow automation.
How It Works
This library acts as a bridge, translating MCP specifications into RubyLLM's conversational interface. It supports multiple transport mechanisms—stdio, streamable HTTP, and sse—allowing flexible communication with MCP servers. Core features include seamless integration of MCP tools, resources, and prompts into RubyLLM chats, robust OAuth 2.1 authentication with PKCE and automatic token refresh, and built-in handlers for real-time progress notifications and logging, facilitating interactive and dynamic LLM applications.
Quick Start & Requirements
Installation involves adding gem "ruby_llm-mcp" to your Gemfile and running bundle install. For Rails applications, a generator rails generate ruby_llm:mcp:install is provided. The filesystem tool example requires bunx. An OPENAI_API_KEY is necessary for RubyLLM configuration. OAuth flows may require an MCP_SERVER_URL. Documentation is available at rubyllm-mcp.com.
Highlighted Details
stdio, streamable, and sse transport types for MCP communication.Maintenance & Community
Contributions via issues and pull requests are welcomed at the project's GitHub repository (patvice/ruby_llm-mcp).
Licensing & Compatibility
Released under the permissive MIT License. This license allows for commercial use and integration into closed-source applications without copyleft restrictions.
Limitations & Caveats
The provided documentation does not explicitly detail known limitations, alpha/beta status, or specific unsupported platforms. Users should consult the issue tracker for potential caveats.
4 months ago
Inactive
PrefectHQ