Introduction
Last week brought a wave of exciting updates from AWS, headlined by the new managed payment capabilities for AI agents in Amazon Bedrock AgentCore. This feature, developed in collaboration with Coinbase and Stripe, allows AI agents to autonomously handle payments for APIs, web content, and more. Alongside this, AWS introduced the Agent Toolkit for AI coding, a new MCP server, preview of WorkSpaces for agents, and faster EC2 instances. Here’s a closer look at these developments.
Amazon Bedrock AgentCore Payments Preview
The most notable launch is the preview of managed payment capabilities within Amazon Bedrock AgentCore. This feature eliminates the need for custom billing, credential management, and compliance systems by enabling agents to pay for external services directly. Partnerships with Coinbase and Stripe allow users to connect a Coinbase CDP wallet or Stripe Privy wallet as a payment connection. You can set session-level spending limits, and your agent will autonomously transact during execution.
Imagine a research agent that pays for real-time market data on the fly, or a coding agent calling paid APIs mid-task. To learn more, visit the official blog post or the documentation, and get started with the AgentCore CLI.
Agent Toolkit for AWS
At no additional charge, AWS released the Agent Toolkit for AWS, a production-ready suite of tools and guidance designed to help AI coding agents build on AWS with fewer errors, lower token costs, and enterprise-grade security. This toolkit is the successor to the MCP servers, plugins, and skills previously available on AWS Labs. You can get started with the quick start guide or browse available skills and plugins on GitHub.
AWS MCP Server Now Generally Available
As part of the Agent Toolkit, the AWS MCP Server is now generally available. This managed remote Model Context Protocol (MCP) server gives AI agents and coding assistants secure, authenticated access to all AWS services through a small, fixed set of tools. For more details, read Sebastian Stormacq’s blog post.
Amazon WorkSpaces for AI Agents (Preview)
In preview, Amazon WorkSpaces now supports AI agents that can securely access and operate desktop applications within managed WorkSpaces environments. This feature enables organizations to automate everyday workflows at scale while maintaining full enterprise-grade governance and compliance. Learn more from Micah Walter’s blog post.
New Amazon EC2 Instances: M8idn/M8idb and R8idn/R8idb
AWS introduced the M8idn/M8idb and R8idn/R8idb instances, powered by custom sixth-generation Intel Xeon Scalable processors available only on AWS, along with the latest sixth-generation AWS Nitro cards. These instances deliver up to 43% better compute performance per vCPU compared to previous-generation instances. The M8idn/R8idn variants offer up to 600 Gbps network bandwidth, while M8idb/R8idb instances provide up to 300 Gbps EBS bandwidth.
Valkey Turns Two: Community Growth
Hitting its two-year anniversary, Valkey has proven that open, community-driven technology can innovate faster and scale further than proprietary models. The project has surpassed 100 million Docker pulls – a 17x increase year over year – and attracted more than 225 contributors who have submitted over [additional details omitted for brevity]. This milestone underscores the value of community-led development in the cloud ecosystem.
Additional Updates
For a full list of AWS announcements, keep an eye on the What’s New with AWS page. Stay tuned for more innovations as AWS continues to expand its AI and infrastructure offerings.