{
  "id": 4735625,
  "title": "Connect an AgentCore Runtime hosted MCP server to Amazon Quick",
  "url": "https://urgent.news/2026/08/31/connect-an-agentcore-runtime-hosted-mcp-server-to-amazon-quick",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-31T22:47:53.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/connect-an-agentcore-runtime-hosted-mcp-server-to-amazon-quick/"
  },
  "original_language": "en",
  "account": "Connecting an AgentCore Runtime hosted MCP server to Amazon Quick is a straightforward process that involves several steps. The first step is to implement and deploy a sample remote MCP server on AgentCore Runtime. This sample MCP server will have basic dummy tools, and all the necessary code and instructions can be found in the AgentCore samples notebook on GitHub.\n\nOnce the MCP server is deployed, the next step is to integrate it with AgentCore Gateway. This integration requires setting up both inbound and outbound authentication. Inbound authentication is handled using Amazon Cognito for user authorization, while Outbound authentication is managed by AgentCore Identity, a dedicated identity and access management service for AI agents.\n\nAfter the MCP server is integrated with AgentCore Gateway, the next step is to register the MCP integration in Amazon Quick and connect it with your chat agent. This integration allows your AI agents to access additional tools and sub-agent capabilities through the MCP server.\n\nOnce the integration is complete, you can test the MCP server integration within Amazon Quick to ensure everything is working as expected. Finally, don't forget to clean up any resources you created during the process to avoid unnecessary costs.",
  "summary": "In this post, you will learn how to deploy and host your MCP server in AgentCore Runtime and integrate it with Amazon Quick, along with the prerequisites. With this pattern, you promote reusability and avoid duplication of AI tools, so clients can reuse commonly used tools and agents exposed through an MCP server instead of authoring them from scratch again. Your customers get a way to use your…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}