Amazon Bedrock AgentCore Payments and AWS Updates: Q&A

This Q&A covers the key announcements from the latest AWS weekly roundup, including the preview of managed payment capabilities in Amazon Bedrock AgentCore, the new Agent Toolkit for AWS, the AWS MCP Server, Amazon WorkSpaces for AI agents, and new EC2 instances. These updates aim to simplify AI agent development, enhance security, and improve performance.

How do the new managed payment capabilities in Amazon Bedrock AgentCore work?

Amazon Bedrock AgentCore now offers managed payment capabilities, enabling AI agents to autonomously access and pay for APIs, MCP servers, web content, and other agents. Built in partnership with Coinbase and Stripe, this feature removes the heavy lifting of building custom billing, credential management, and compliance systems. You connect a Coinbase CDP wallet or Stripe Privy wallet as a payment connection, set session-level spending limits, and your agent transacts autonomously during execution. For example, a research agent can pay for real-time market data on the fly, or a coding agent can call paid APIs mid-task. This breakthrough allows agents to handle financial transactions seamlessly within their workflows. For deeper details, refer to the AgentCore documentation and the official blog post.

What is the Agent Toolkit for AWS and how does it benefit AI coding agents?

The Agent Toolkit for AWS is a production-ready suite of tools and guidance, available at no additional charge, that helps AI coding agents build on AWS with fewer errors, lower token costs, and enterprise-grade security controls. It is the successor to the MCP servers, plugins, and skills previously available on AWS Labs. The toolkit includes a quick start guide and a variety of skills and plugins on GitHub, enabling developers to integrate AI agents more efficiently. By providing pre-built components and best practices, it reduces development time and ensures compliance with enterprise standards. AI agents can now interact with AWS services more reliably, making it easier to automate complex tasks without sacrificing security or performance.

What is the AWS MCP Server and when is it available?

The AWS MCP Server is a managed remote Model Context Protocol (MCP) server that gives AI agents and coding assistants secure, authenticated access to all AWS services through a small, fixed set of tools. It is now generally available and part of the Agent Toolkit for AWS. This server simplifies how agents interact with AWS by providing a standardized interface, reducing the need for custom integrations. Developers can use it to enable AI agents to perform actions like managing resources, querying data, or orchestrating workflows—all with enterprise-grade authentication and authorization. For a complete overview, see Seb Stormacq’s blog post.

How can Amazon WorkSpaces for AI agents be used in daily operations?

Currently in preview, Amazon WorkSpaces for AI agents allows AI agents to securely access and operate desktop applications through managed WorkSpaces environments. This capability enables organizations to automate everyday workflows at scale while maintaining full enterprise-grade governance and compliance. For instance, an AI agent could automate data entry in a desktop application, generate reports, or perform repetitive tasks that traditionally required human intervention. All actions are logged and controlled, ensuring audit trails and security policies are enforced. This preview opens up new possibilities for automating desktop-heavy processes without compromising on control. More details are available in Micah Walter’s blog post.

What performance improvements do the new EC2 M8idn/M8idb and R8idn/R8idb instances offer?

The new Amazon EC2 M8idn/M8idb and R8idn/R8idb instances are powered by custom sixth-generation Intel Xeon Scalable processors available only on AWS, combined with the latest sixth-generation AWS Nitro cards. They deliver up to 43% better compute performance per vCPU compared to previous-generation instances. Additionally, M8idn/R8idn instances offer up to 600 Gbps network bandwidth, while M8idb/R8idb instances provide up to 300 Gbps EBS bandwidth. These enhancements make them ideal for memory-intensive and compute-heavy workloads such as databases, caching, real-time analytics, and high-performance computing. For a full list of AWS announcements, visit the What’s New with AWS page.

What milestones has Valkey achieved recently?

Valkey, the open-source fork of Redis, recently celebrated its second anniversary. It has surpassed 100 million Docker pulls, a 17x increase year-over-year, and attracted more than 225 contributors who have submitted over [number of contributions]. According to AWS, Valkey demonstrates that open, community-driven technology can innovate faster, scale further, and deliver more value than any single-vendor model. This milestone underscores the growing adoption of Valkey as a reliable, high-performance in-memory data store, especially for applications requiring low latency and high throughput. The community continues to enhance its capabilities, making it a strong alternative for Redis users seeking an open-source solution with active development.