It feels like almost everyone building AI applications and agents is talking about the Model Context Protocol (MCP), as well as building MCP servers that you install and run locally on your own computer. However, with Cloudflare's support for remote MCP servers, developers can now build and deploy these servers to Cloudflare, providing a more accessible way for people to use AI applications and agents. This enables the wider audience of Internet users who aren't going to install and run MCP servers locally for use with desktop apps, allowing them to continue tasks across devices and log in and have things just work. Remote MCP servers are accessible on the Internet, and people simply sign in and grant permissions to MCP clients using familiar authorization flows. This opens up new ways of working with LLMs and agents to a much wider audience, including more everyday consumer use cases. The Model Context Protocol is quickly becoming the common protocol that enables LLMs to go beyond inference and RAG, and take actions that require access beyond the AI application itself, such as sending an email or deploying a code change.