agentregistry-dev/agentregistry

Fast-track AI innovation with a centralized, trusted, curated registry

What it solves

AgentRegistry provides a centralized platform to manage the fragmented ecosystem of AI building blocks. It eliminates the need for developers to manually track and configure MCP servers, agents, skills, and prompts spread across various package managers (npm, PyPI) and repositories, providing a single trusted source of truth for an organization's AI assets.

How it works

It functions as a registry and management layer with a CLI (arctl) and a Web UI. Users can package and publish artifacts—such as MCP servers, structured knowledge packages (skills), and agent definitions—into the registry. These artifacts can then be discovered, versioned, and deployed either locally via Docker or to Kubernetes clusters using Helm. It also integrates with AI clients like Claude Desktop, Cursor, and VS Code to automate IDE configuration.

Who it’s for

  • Platform Teams: To curate, approve, and govern the AI tools and agents available to their organization.
  • Developers: To build, test, and deploy AI artifacts with minimal manual configuration and a consistent workflow from local development to production.

Highlights

  • Unified Catalog: A single place to register and manage MCP servers, agents, skills, and prompts.
  • Multi-source Support: Supports artifacts from npm, PyPI, Docker/OCI images, and remote HTTP/SSE endpoints.
  • ** Firestore-like experience for AI:** Provides scaffolding tools (arctl init) and one-command publishing.
  • IDE Integration: Automatically generates configurations for popular AI-enabled IDEs (Cursor, VS Code) and Claude Desktop.
  • Enterprise Governance: Centralized control over versioning, metadata, and security approvals before company-wide deployment.

Related

  • Project
    tech-leads-club/agent-skills

    A secure, validated skill registry and CLI for extending AI coding agents with verified, safe, and tested capabilities.

  • Project
    agentic-community/mcp-gateway-registry

    A unified control plane and gateway for AI assets, providing centralized discovery, governance, and secure access to MCP servers, agents, and model inference endpoints.

  • Project
    IBM/mcp-context-forge

    ContextForge is an open‑source gateway that federates MCP, A2A, REST and gRPC services into a single, centrally governed endpoint for AI agents and tools. It provides auth, rate‑limiting, OpenTelemetry tracing, a plug‑in system, and an admin UI, and can be run via PyPI, Docker, or Helm.

  • Project
    UsefulSoftwareCo/executor

    An open-source integration layer that centralizes tool configurations, authentication, and policies for AI agents via the Model Context Protocol (MCP).

  • Project
    docker/mcp-registry

    A curated registry of Model Context Protocol (MCP) servers that allows developers to discover and deploy secure, containerized tools for AI assistants.