toolhive-registry-server and toolhive-catalog

The catalog provides the curated data source of MCP servers while the registry server implements the standardized API layer for programmatic access to that catalog, making them complements designed to work together in a registry infrastructure.

toolhive-registry-server
50
Established
toolhive-catalog
48
Emerging
Maintenance 13/25
Adoption 5/25
Maturity 15/25
Community 17/25
Maintenance 10/25
Adoption 6/25
Maturity 15/25
Community 17/25
Stars: 14
Forks: 8
Downloads:
Commits (30d): 0
Language: Go
License: Apache-2.0
Stars: 18
Forks: 8
Downloads:
Commits (30d): 0
Language: Go
License: Apache-2.0
No Package No Dependents
No Package No Dependents

About toolhive-registry-server

stacklok/toolhive-registry-server

An API server that implements the official MCP Registry API, providing standardised access to MCP servers from multiple backends, including file-based and other API-compliant registries.

Supports multiple registry sources (Git, file, API, Kubernetes) with automatic background synchronization and configurable retry logic, aggregating them into a unified catalog. Built with clean layered architecture using Chi router for HTTP handling and PostgreSQL for scalable metadata storage. Integrates with ToolHive Enterprise UI and Kubernetes operators through OAuth 2.0/OIDC authentication, enabling enterprise governance with audit trails and standards-compliant API endpoints.

About toolhive-catalog

stacklok/toolhive-catalog

ToolHive's registry catalog of MCP servers

This is a catalog for AI assistant developers to discover and register specialized tools and reusable workflows. It helps developers list new servers offering capabilities like GitHub integration or database querying, and share 'skills' which are pre-built prompts and workflows. The output is a public listing within the ToolHive ecosystem, making your AI assistant features available to others.

AI-Assistant-Development AI-Workflow-Automation Tool-Integration AI-Skill-Sharing Prompt-Engineering

Scores updated daily from GitHub, PyPI, and npm data. How scores work