AWS Open Sources MCP Gateway and Registry for AI Asset Governance
AWS has released the open-source MCP Gateway and Registry, an Apache 2.0 licensed project designed to help enterprises govern and discover AI assets at scale. This tool addresses the need for both human users and AI agents to access approved AI resources, functioning similarly to enterprise data and software catalogs but with an AI-first focus. It offers a UI for humans and a machine-readable API for AI agents, with deployment options on Kubernetes (EKS) or serverless (ECS Fargate), and supports federation with other registries.
- →Centralized governance and discovery for AI assets
- →MCP Gateway for unified access and security
- →AI Registry Tools for agent interaction
- →Support for custom AI asset types
- →Federation capabilities for distributed registries
Features (6) ›
- Centralized governance and discovery for AI assets
The MCP Gateway and Registry provides a unified catalog for AI assets like servers, agents, and skills, enabling enterprises to govern and discover these resources. It includes a React-based UI with fine-grained access control for human users and a programmatic API for AI agents.
- MCP Gateway for unified access and security
The optional MCP Gateway acts as a single entry point for AI assets, simplifying network plumbing, enforcing fine-grained access control, and providing an audit trail for tool calls. It supports authentication for both human users and AI agents.
- AI Registry Tools for agent interaction
The AI Registry Tools MCP server allows AI agents to list and semantically search for AI assets through a standard MCP interface, facilitating peer-to-peer communication and discovery.
- Support for custom AI asset types
Beyond built-in asset types, the registry supports custom entities defined by organizations, such as workflows or prompt templates, allowing for centralized management of diverse AI-related resources.
- Federation capabilities for distributed registries
The registry can federate with other instances of itself, third-party registries, and AWS services like Amazon Bedrock AgentCore, providing a single view across an organization's AI assets while allowing decentralized management.
- Integrated supply-chain security, identity, and observability
The registry incorporates open-source security scanners, integrates with common identity providers for authentication and authorization, and exports observability data (traces, metrics) to existing backends via OpenTelemetry.
https://aws.amazon.com/blogs/opensource/governing-ai-assets-at-scale-with-mcp-gateway-and-registry/
Related releases
- Build Stateful IT Service Desk Agent with LangGraph on EKS AWS Open Source Blog ·
- AWS introduces Loom for secure AI agent development and deployment AWS Open Source Blog ·
- AWS Open Data Registry Adds AI-Powered Dataset Discovery AWS Open Source Blog ·
- AWS WAF adds AI traffic monetization to charge bots for content access AWS News Blog ·
- Amazon EC2 G7 instances with NVIDIA RTX PRO 4500 GPUs now available AWS News Blog ·
- AWS Supports New Open Governance Model for MySQL AWS Open Source Blog ·