MCP server for Agentation - visual feedback for AI coding agents
Visual feedback for AI coding agents
MCP server that exposes Re-agentation annotation batches to Claude Code / Claude Desktop (stdio) and to Cursor / Windsurf / other clients (HTTP+SSE).
Visual feedback tool for AI coding agents — Vue 2.7 & 3
Dev-mode Svelte inspector for annotating elements, text selections, groups, and areas in the browser.
MCP server for Agentation - visual feedback for AI coding agents
Visual feedback for AI coding agents - Vue 3 version
React Native dev-only probe overlay — tap a component, annotate it, batch into a single AI edit request. Part of Re-agentation.
Playwright Tools for MCP
Model Context Protocol implementation for TypeScript
Command-Line Interface for Firebase
A TypeScript SSE proxy for MCP servers that use stdio transport.
A high-level API to control headless Chrome over the DevTools Protocol
Help agents automatically write and test stories for your UI components
The official TypeScript library for the Cloudflare API
Vue 3 UI components: toolbar, overlay, popover, highlight & marker layers
MCP server for Chrome DevTools
Add MCP servers to your favorite coding agents with a single command.
MCP server for Context7
Pi extension that receives Agentation webhooks and turns them into queued user messages
A high-level API to control headless Chrome over the DevTools Protocol
MCP Apps SDK — Enable MCP servers to display interactive user interfaces in conversational clients.
mcp-ui Client SDK
The official TypeScript library for the Turbopuffer API
Build AI agents with declarative DSL and Model Context Protocol support
Lightweight gem, tested in large Rails codebases (20k+ Ruby files). Allows AI assistants to evaluate and verify rails/ruby code changes securely at lighting-speed access without the need to restart server or run bundler.
Rails Engine that captures exceptions, stores them in your database with rich context, and exposes error data via a bundled MCP server so AI agents can triage, resolve, and fix errors autonomously.
Embeds a FOSM-aware MCP server and ACP agent into your Rails development environment, giving coding agents (Claude Code, Codex, Copilot) runtime intelligence: database queries, logs, code evaluation, and deep introspection of FOSM lifecycle definitions, state machines, transitions, guards, and audit trails. Built on the FOSM (Finite Object State Machine) paradigm — declarative lifecycles for business objects where AI agents operate within bounded, auditable state machines.
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.
Yorishiro is a CLI-based LLM agent that supports multiple providers (Anthropic, OpenAI, Ollama), built-in tools for file operations and command execution, MCP server integration, and plan mode.
Encrypted local vault for secrets with MCP server for AI agents. No cloud required. Powers credentials management at inventlist.com.
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.
pikuri-mcp adds Model Context Protocol support to pikuri-core agents: a +Pikuri::Mcp::Registry+ for declaring stdio + HTTP MCP servers, the +Pikuri::Mcp::Servers+ runtime that spawns them, a +Pikuri::Mcp::Synthesizer+ that LLM-fills missing server descriptions, a +Pikuri::Mcp::Verifier+ that screens server surfaces for prompt-injection patterns before any tool is advertised to the LLM, and a +Pikuri::Mcp::Extension+ that wires everything into a +Pikuri::Agent+ via +c.add_extension(...)+ in the +Agent.new+ block.
A Model Context Protocol (MCP) server that enables AI agents to query information about gems in a Ruby project's Gemfile, including source code and metadata.
Agentf is a Ruby-native multi-agent workflow engine with an ORCHESTRATOR, role-specialized agents, provider adapters (OpenCode/Copilot), and Redis-backed semantic, episodic, and graph-style memory. It includes a unified CLI, MCP server tools, and install/update workflows for generated agent/command manifests.
A Model Context Protocol (MCP) server that allows AI agents to start, stop, and monitor Rails development servers