The Model Context Protocol (MCP) Proxy for AWS is now generally available
Today, AWS announces the general availability of the Model Context Protocol (MCP) Proxy for AWS, a client-side proxy that enables MCP clients to connect to remote, AWS-hosted MCP servers using AWS SigV4 authentication. The Proxy supports popular agentic AI development tools like Amazon Q Developer CLI, Kiro, Cursor, and popular agent frameworks like Strands Agents. Customers can connect to remote MCP servers with AWS credentials using the Proxy to automatically handle MCP protocol communications via SigV4. The Proxy also helps customers to connect to MCP servers built on Amazon Bedrock AgentCore Gateway or Runtime using SigV4 authentication.
This release allows developers and agents to extend development workflows to include AWS service interactions from AWS MCP server tools. For example, you can use AWS MCP servers to work with resources like AWS S3 buckets or Amazon RDS tables through existing MCP servers with SigV4. The MCP Proxy for AWS includes safety controls such as read-only mode to prevent unintended changes, configurable retry logic for reliability, and logging for troubleshooting. Customers can install the Proxy from source, through Python package managers, or by using a container making it simple to configure with their preferred MCP-supported development tool.
The MCP Proxy for AWS is open-source and available now. Visit the AWS GitHub repository to view the installation and configuration options and start connecting with remote AWS MCP Servers today.