AWS Enhances AI Agent Development with Managed Payments and New Toolkits

In a significant update for developers building AI-powered agents, AWS has introduced a series of new capabilities and tools designed to simplify and accelerate agent development. The most notable announcement is the preview of managed payment functionalities within Amazon Bedrock AgentCore, which enables AI agents to autonomously pay for APIs, web content, and other services. This release, along with the launch of the Agent Toolkit for AWS, general availability of the AWS MCP Server, and new EC2 instances, marks a major step forward in making agent-based workflows more practical and cost-effective.

Amazon Bedrock AgentCore Payment Capabilities

Amazon Bedrock AgentCore is now previewing a managed payment system that allows AI agents to handle transactions on the fly. Developed in collaboration with Coinbase and Stripe, this feature eliminates the need for developers to build custom billing, credential management, and compliance systems. Instead, agents can be configured to use a Coinbase CDP wallet or Stripe Privy wallet as a payment connection, with session-level spending limits set by the developer. During execution, the agent autonomously pays for required services.

This capability opens up new possibilities, such as a research agent that can purchase real-time market data mid-task, or a coding agent that calls paid APIs without manual intervention. For more details, refer to the official blog post and the documentation. Developers can get started using the AgentCore CLI.

Agent Toolkit for AWS

Another key release is the Agent Toolkit for AWS, a production-ready suite of tools and guidance available at no additional charge. This toolkit helps AI coding agents build on AWS with fewer errors, lower token costs, and enterprise-grade security controls. It is the successor to the earlier MCP servers, plugins, and skills available on AWS Labs. Developers can start with the quick start guide or explore available skills and plugins on GitHub.

AWS MCP Server Now Generally Available

The AWS MCP Server is now generally available as part of the Agent Toolkit. 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. It simplifies integration and reduces complexity. Learn more in Seb Stormacq's blog post.

Amazon WorkSpaces for AI Agents (Preview)

AWS has also previewed Amazon WorkSpaces for AI agents, enabling agents to securely access and operate desktop applications within managed WorkSpaces environments. This capability allows organizations to automate everyday workflows at scale while maintaining enterprise-grade governance and compliance. For further information, see Micah Walter's blog post.

New EC2 Instances: M8idn/M8idb and R8idn/R8idb

AWS introduced new EC2 instances powered by custom sixth-generation Intel Xeon Scalable processors available only on AWS, combined 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 and R8idn instances offer up to 600 Gbps network bandwidth, while the M8idb and R8idb instances provide up to 300 Gbps EBS bandwidth. These improvements are ideal for memory-intensive and network-heavy workloads.

Valkey Community Milestone

Finally, the open-source project Valkey celebrates its second anniversary, demonstrating the power of community-driven development. Valkey has surpassed 100 million Docker pulls (up 17x year over year) and attracted over 225 contributors. This growth underscores the value of open, collaborative innovation over single-vendor models.

For a complete list of AWS announcements, visit the What's New with AWS page.