{"version":1,"type":"story","url":"https://digestai.news/story/aws-demonstrates-building-a-semantic-layer-with-atscale-and-bedrock-ag","json":"https://digestai.news/story/aws-demonstrates-building-a-semantic-layer-with-atscale-and-bedrock-ag.json","markdown":"https://digestai.news/story/aws-demonstrates-building-a-semantic-layer-with-atscale-and-bedrock-ag.md","slug":"aws-demonstrates-building-a-semantic-layer-with-atscale-and-bedrock-ag","headline":"AWS launches generally available Agent Registry for runtime tool discovery","summary":"AWS announced that its Agent Registry service is generally available, offering a managed, searchable catalog of Model Context Protocol (MCP) servers, agents, and agent skills. Publishers register protocol‑specific descriptors and searchable descriptions, while orchestrators query the registry at runtime to discover the appropriate capability, instantiate a client, and execute the request.\n\nThe blog post walks through a Python sample that deploys an order‑management MCP server through Amazon Bedrock AgentCore Gateway, two agent‑to‑agent (A2A) agents, the Registry, and an orchestrator. Three demo scenarios illustrate the discover‑instantiate‑execute loop: an MCP‑only order status query, a combined MCP + A2A pricing and discount flow, and a semantic match for a return‑and‑refund intent that does not appear in any tool name. The sample shows how authentication (Cognito OAuth for Gateway, IAM‑signed Boto3 calls for A2A) remains separate from discovery, and how governance via approval workflows controls which records become discoverable.","keyPoints":["AWS Agent Registry provides a governed, searchable catalog for MCP servers, agents, and skills, enabling runtime discovery.","The sample demonstrates a discover‑instantiate‑execute loop using Bedrock AgentCore, Cognito, Lambda, and other AWS services.","Runtime discovery decouples tool publishing from orchestrator code, allowing new capabilities without redeploying the orchestrator."],"whyItMatters":"Runtime discovery lets enterprise AI agents scale by reducing hard‑coded tool wiring, improving agility and governance for large internal API catalogs.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["AWS","Amazon Bedrock","Amazon Cognito","Amazon Lambda","Amazon Secrets Manager"],"models":["Anthropic Claude Sonnet"],"people":[]},"firstPublishedAt":"2026-10-20T15:33:54Z","updatedAt":"2026-10-20T16:22:24Z","sourceCount":4,"hasPrimarySource":true,"sources":[{"outlet":"AWS Machine Learning Blog","title":"Discover tools at runtime with AWS Agent Registry","url":"https://aws.amazon.com/blogs/machine-learning/discover-tools-at-runtime-with-aws-agent-registry","publishedAt":"2026-10-20T16:22:24Z","type":"primary","primary":true,"lead":true},{"outlet":"AWS Machine Learning Blog","title":"Build a semantic layer for agentic AI on AWS with Denodo and Amazon Bedrock AgentCore","url":"https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-denodo-and-amazon-bedrock-agentcore","publishedAt":"2026-10-20T15:39:04Z","type":"primary","primary":true,"lead":false},{"outlet":"AWS Machine Learning Blog","title":"Build a semantic layer for agentic AI on AWS with Strategy Mosaic and Amazon Bedrock AgentCore","url":"https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-strategy-mosaic-and-amazon-bedrock-agentcore","publishedAt":"2026-10-20T15:36:39Z","type":"primary","primary":true,"lead":false},{"outlet":"AWS Machine Learning Blog","title":"Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore","url":"https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-atscale-and-amazon-bedrock-agentcore","publishedAt":"2026-10-20T15:33:54Z","type":"primary","primary":true,"lead":false}],"sourceNotes":null,"discussions":[],"thread":{"title":"Securing the Future of Autonomous AI Agents","url":"https://digestai.news/thread/aws-outlines-trust-in-depth-for-safer-ai-agent-autonomy","storyCount":5},"cite":{"text":"Digest AI, \"AWS launches generally available Agent Registry for runtime tool discovery\", 20 October 2026, https://digestai.news/story/aws-demonstrates-building-a-semantic-layer-with-atscale-and-bedrock-ag","publisher":"Digest AI","title":"AWS launches generally available Agent Registry for runtime tool discovery","datePublished":"2026-10-20T15:33:54Z","url":"https://digestai.news/story/aws-demonstrates-building-a-semantic-layer-with-atscale-and-bedrock-ag"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}