tag: AgentCore · Bartek Chojnacki

Bridging the Gap: Cloud AI Agents Meeting Local Tools

Ever wondered how to let your cloud-hosted AI agent on Amazon Bedrock AgentCore access tools sitting on your laptop? This article walks you through building a secure MCP bridge that tunnels signed messages over WebSocket through a browser extension and Chrome native messaging—no open ports or VPN headaches needed.

> source: aws.amazon.com

Deploy AI Agents in n8n with Amazon Bedrock AgentCore

Amazon Bedrock AgentCore is now generally available, letting you build production-ready AI agents directly in n8n workflows without touching infrastructure code. The new community node gives you persistent memory, real tool integration, code execution, and VPC isolation—all from the n8n editor.

> source: aws.amazon.com

Amazon Bedrock AgentCore Security Flaw Lets Users Bypass AI Safety Guards

Amazon Bedrock AgentCore's InvokeHarness API has a nasty input validation bug (CVE-2026-18830) that lets authenticated users trigger configured tools without the AI model checking them first. If your harness has tools set up, attackers could invoke them directly, skipping all those safety controls you've got in place. The good news? Impact is limited to whatever tools you've actually configured—empty harnesses are safe. You'll want to update immediately if you're running versions before July 31, 2026.

> source: aws.amazon.com

Build AI Agents Without Code Using Amazon Bedrock AgentCore

Amazon Bedrock AgentCore lets you spin up autonomous AI agents that query multiple data sources through natural language—no custom coding needed. With MCP server connectors, role-based access control, and persistent memory built in, enterprises can enforce security boundaries automatically while getting cross-system business intelligence.

> source: aws.amazon.com