Agent Registry

A comprehensive platform for discovering, deploying, and managing MCP (Model Context Protocol) servers, agents and skills

Agent Registry is a unified system that combines a centralized registry, runtime management, and development tooling for MCP servers, agents and skills. It enables teams to publish, discover, and deploy AI agent capabilities as composable services.

🎯 What is Agent Registry?

Agent Registry solves the challenge of managing AI agent capabilities by providing:

• 📦 Centralized Registry: Discover and publish MCP servers, skills, and agents
• 🚀 Automated Deployment: Deploy MCP servers locally or remotely with one command
• 🔧 Developer Tools: Scaffolding and code generators for Python and Go MCP servers
• 🌐 Web UI: Beautiful dashboard for managing your agent ecosystem
• 🔌 Agent Gateway: Unified endpoint for all your MCP servers
• 🐳 Container Orchestration: Automated Docker Compose management

🏗️ Architecture

Operation

Development

🚀 Quick Start

Prerequisites

• Docker Desktop with Docker Compose v2+
• Go 1.25+ (for building from source)

Installation

# Install via script (recommended)
curl -fsSL https://raw.githubusercontent.com/agentregistry-dev/agentregistry/main/scripts/get-arctl | bash

# Or download binary directly from releases
# https://github.com/agentregistry-dev/agentregistry/releases

Start the Registry

# Start the registry server and look for available MCP servers
arctl mcp list

# The first time the CLI runs it will automatically start the registry server daemon and import the built-in seed data.

Access the Web UI

# Launch the embedded web interface
arctl ui

# Open http://localhost:8080 in your browser

📚 Core Concepts

MCP Servers

MCP (Model Context Protocol) servers are services that provide tools, resources, and prompts to AI agents. They're the building blocks of agent capabilities.

Agent Gateway

The Agent Gateway is a reverse proxy that provides a single MCP endpoint for all deployed servers:

sequenceDiagram
    participant IDE as AI IDE/Client
    participant GW as Agent Gateway
    participant FS as filesystem MCP
    participant GH as github MCP
    
    IDE->>GW: Connect (MCP over HTTP)
    GW-->>IDE: Available tools from all servers
    
    IDE->>GW: Call read_file()
    GW->>FS: Forward to filesystem
    FS-->>GW: File contents
    GW-->>IDE: Return result
    
    IDE->>GW: Call create_issue()
    GW->>GH: Forward to github
    GH-->>GW: Issue created
    GW-->>IDE: Return result

Loading

IDE Configuration

Configure your AI-powered IDEs to use the Agent Gateway:

# Generate Claude Desktop config
arctl configure claude-desktop

# Generate Cursor config
arctl configure cursor

# Generate VS Code config
arctl configure vscode

🎨 Web UI

The embedded web interface provides a visual dashboard for:

• 📊 Dashboard: Overview of servers, deployments, and statistics
• 🔍 Discovery: Browse and search the registry
• 🚀 Deployments: Visual deployment management
• ⚙️ Configuration: Server settings and environment variables
• 📈 Monitoring: Deployment status and health

🤝 Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

Development setup:

See DEVELOPMENT.md for detailed architecture information.

📄 License

MIT License - see LICENSE for details.

🔗 Related Projects

• Model Context Protocol
• kagent
• MCP Go SDK
• FastMCP

📞 Support

• 📖 Documentation
• 💬 GitHub Discussions
• 🐛 Issue Tracker
• 📧 Email: support@agentregistry.dev

---

Built with ❤️ for the AI agent community