Introduction
In a week packed with announcements, AWS unveiled transformative capabilities for AI agents, developer tools, and compute instances. The standout is the new managed payment system for Amazon Bedrock AgentCore, enabling agents to autonomously handle transactions. Alongside this, the release of the Agent Toolkit for AWS and general availability of the AWS MCP Server promise to streamline agent development. Let's dive into the key updates from last week.

Amazon Bedrock AgentCore Payments – Now in Preview
The most exciting development is the first managed payment capability for AI agents, announced in preview for Amazon Bedrock AgentCore. Built in collaboration with Coinbase and Stripe, this feature allows agents to autonomously access and pay for APIs, MCP servers, web content, and even other agents. By handling billing, credential management, and compliance behind the scenes, it eliminates the heavy lifting of building custom systems.
You can connect a Coinbase CDP wallet or a Stripe Privy wallet as a payment connection, set session-level spending limits, and let your agent transact independently during execution. This unlocks powerful use cases: a research agent that pays for real-time market data on the fly, or a coding agent that calls paid APIs mid-task without human intervention.
To learn more, visit the official blog post, explore the documentation, and get started with the AgentCore CLI.
Agent Toolkit for AWS – Production-Ready Suite
Also launched last week, the Agent Toolkit for AWS is a comprehensive, production-ready suite of tools and guidance available at no additional charge. It helps AI coding agents build on AWS with fewer errors, lower token costs, and enterprise-grade security controls. This toolkit succeeds the earlier MCP servers, plugins, and skills available on AWS Labs.
To get started, refer to the quick start guide or browse the available skills and plugins on GitHub.
AWS MCP Server – Now Generally Available
As part of the Agent Toolkit, the AWS MCP Server (Model Context Protocol) is now generally available. This managed remote server gives AI agents and coding assistants secure, authenticated access to all AWS services through a small, fixed set of tools. It simplifies integration and reduces the complexity of building custom connectors. For more details, see Seb Stormacq’s blog post.

New Amazon WorkSpaces for AI Agents (Preview)
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. It’s a significant step toward autonomous desktop task execution. For deeper insights, read Micah Walter’s blog post.
New Amazon EC2 Instances: Enhanced Performance
AWS announced new EC2 instance families: M8idn/M8idb and R8idn/R8idb, powered by custom sixth-generation Intel Xeon Scalable processors available only on AWS, paired with the latest sixth-generation AWS Nitro cards. These instances deliver up to 43% better compute performance per vCPU compared to previous-generation instances.
- M8idn/R8idn instances offer up to 600 Gbps network bandwidth.
- M8idb/R8idb instances deliver up to 300 Gbps EBS bandwidth.
These improvements are ideal for memory-intensive and data-heavy workloads. For a full list of AWS announcements, visit the What’s New with AWS page.
Valkey Turns Two – Community Success
Finally, the open-source in-memory data store Valkey celebrated its second anniversary. Valkey stands as proof that open, community-driven technology innovates faster and scales further than single-vendor models. It has surpassed 100 million Docker pulls (up 17x year over year) and attracted over 225 contributors who have submitted more than 1,000 commits. This growth highlights the power of community collaboration.
Conclusion
From enabling AI agents to handle payments autonomously, to providing a robust toolkit for developers and boosting compute performance, these updates reflect AWS’s commitment to innovation and practical solutions. Stay tuned for more advancements in the coming weeks.