The Model Context Protocol (MCP) is being updated with new capabilities to make it easier for developers to bring their services into the AI ecosystem. Two new features, Streamable HTTP Transport and Python language support, are being added to the MCP protocol. The Streamable HTTP transport simplifies communication between AI agents and services by using a single HTTP endpoint for sending and receiving responses, replacing the need to implement separate endpoints for initializing the connection and for sending messages. This feature provides bi-directional communication, automatic connection upgrades, and reduces complexity in setting up remote connections. Python language support allows developers to build MCP servers on Cloudflare that are entirely written in Python, making it easier to use MCP with existing Python development workflows. The new capabilities aim to improve the scalability and reliability of interactions between AI agents and services, while maintaining backward compatibility with existing clients.