A smart proxy and interactive REPL for Model Context Protocol (MCP) servers
Cloud Run MCP deployment tool
Run MCP stdio servers over SSE, Streamable HTTP or visa versa
CLI for Google Search Console - dump, query, and run MCP server
Run MCP SuperAssistant over SSE or visa versa
Cloud Run MCP deployment tool
Cloud Run MCP deployment tool
Run MCP stdio servers over SSE or visa versa
Run MCP stdio servers over SSE, Streamable HTTP
OpenAPI-to-Vurb Server Generator. Parses OpenAPI 3.x and Swagger 2.0 specs and generates a complete, ready-to-run MCP Server with full MVA tool stacks (Presenters, Tools, Registry, Server) — all features configurable via YAML.
Run Model Context Protocol (MCP) servers with AWS Lambda
Shared MCP proxy infrastructure - run MCP servers once, share across tools
CLI to run MCP server from Social Shots project
Run MCP stdio servers over Streamable HTTP
Command-line interface for Ksefnik — fetch KSeF invoices, reconcile with bank statements, run MCP server
DataWorks MCP Server: Export the DataWorks Open API to MCP Server, allowing clients that can run MCP Server to use DataWorks Open API through AI.
Run MCP stdio servers over SSE or visa versa
OpenAPI-to-MCP mcpfusion Server Generator. Parses OpenAPI 3.x and Swagger 2.0 specs and generates a complete, ready-to-run MCP Server with full MVA tool stacks (Presenters, Tools, Registry, Server) — all features configurable via YAML.
Convert any documentation URL into a ready-to-run MCP server — 100% local, no API keys needed
Run MCP stdio servers over SSE, Streamable HTTP or visa versa
Model Context Protocol implementation for TypeScript
Run MCP stdio servers over SSE, Streamable HTTP or visa versa
Official MCP server for AgentPay. Lets agents charge vendors, check budgets, and inspect quota through any MCP-compatible client (Claude Desktop, Cursor, etc.).
Run MCP stdio servers over SSE or visa versa
A thin Rails layer over the official MCP Ruby SDK. Mounts a Streamable HTTP MCP endpoint, gates access behind API-key or HTTP Basic auth, enforces fail-closed per-tool database roles, and ships six bundled plugins (DB, Jobs, Flipper, Health, Rake, Custom Tools) plus a Ruby DSL for writing your own.
DynamicMcp lets you get an MCP server up an running in seconds and automatically exposes tools, resources, and prompts as you drop them into their designated directories.
CompletionKit is a prompt testing platform that runs as a Rails engine or a standalone app. Run prompts against real datasets, score every output with an LLM judge against criteria you define, track prompt versions, and get AI-generated improvement suggestions grounded in your actual results. Includes a web UI, REST API, and a built-in MCP server with 34 tools.
Claude Swarm enables you to run multiple Claude Code instances that communicate with each other via MCP (Model Context Protocol). Create AI development teams where each instance has specialized roles, tools, and directory contexts. Define your swarm topology in simple YAML and let Claude instances collaborate across codebases. Perfect for complex projects requiring specialized AI agents for frontend, backend, testing, DevOps, or research tasks.
SwarmSDK is a complete reimagining of Claude Swarm that runs all AI agents in a single process using RubyLLM for LLM interactions. Define collaborative AI agents in simple Markdown files with YAML frontmatter, and orchestrate them without the overhead of multiple processes or MCP inter-process communication. Perfect for building lightweight, efficient AI agent teams with specialized roles and capabilities.
Rails Active MCP enables secure Rails console access through Model Context Protocol (MCP) for AI agents and development tools like Claude Desktop. Provides safe database querying, model introspection, and code execution with comprehensive safety checks and audit logging. Features include: • Safe Ruby code execution with configurable safety checks • Read-only database query tools with result limiting • Rails model introspection (schema, associations, validations) • Dry-run code analysis for safety validation • Environment-specific configuration presets • Comprehensive audit logging and monitoring • Claude Desktop integration out of the box
rails-ai-context turns your running Rails app into the source of truth for AI coding assistants. Instead of guessing from training data or stale file reads, agents query 38 live tools (via MCP server or CLI) to get your actual schema, associations, routes, inherited filters, conventions, and test patterns. Semantic validation catches cross-file errors (wrong columns, missing partials, broken routes) before code runs — so AI writes correct code on the first try. Auto-generates context files for Claude Code, Cursor, GitHub Copilot, OpenCode, and Codex CLI. Works standalone or in-Gemfile.
llm.rb is Ruby's most capable AI runtime. It runs on Ruby's standard library by default. loads optional pieces only when needed, and offers a single runtime for providers, agents, tools, skills, MCP, A2A (Agent2Agent), RAG (vector stores & embeddings), streaming, files, and persisted state. As a bonus, llm.rb is also available for mruby. It supports OpenAI, OpenAI-compatible endpoints, Anthropic, Google Gemini, DeepSeek, xAI, Z.ai, AWS Bedrock, Ollama, and llama.cpp. It also includes built-in ActiveRecord and Sequel support, plus concurrent tool execution through threads, tasks (via async gem), fibers, ractors, and fork (via xchan.rb gem).
RailsLLM integrates the llm.rb runtime and its features into Rails. RailsLLM extends the builtin ActiveRecord support available to the llm.rb runtime with a Rails integration that includes generators for getting set up quickly, and an engine for a stream-capable chat interface that can be extended with your own tools. The llm.rb runtime runs on Ruby's standard library by default. loads optional pieces only when needed, and offers a single runtime for providers, agents, tools, skills, MCP, A2A (Agent2Agent), RAG (vector stores & embeddings), streaming, files, and persisted state.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.