Cloudflare, a global cloud service provider, has announced that it will accelerate the growth of Model Context Protocol (MCP) servers by enabling builders to create and deploy remote MCP servers on its platform.
MCP servers have made it easy to extend the functionalities of AI applications. It is arguably the new HTTP for AI. To facilitate making MCP servers, Cloudflare has added four things to its platform.
The tools include workers-auth-provider (an OAuth provider), McpAgent (a class built into the Cloudflare Agents SDK), mcp-remote (an adapter for MCP clients to work with remote MCP servers), and an AI playground (a chat interface to connect to MCP servers).
Cloudflare lets one build an example MCP server in about two minutes using a single button, guiding the users through everything, if logged in to Cloudflare.
The company mentioned that the benefit of remote MCP servers is that they are accessible on the Internet. “People simply sign in and grant permissions to MCP clients using familiar authorization flows,” it said.
Cloudflare added, “We think this is going to be a massive deal—connecting coding agents to MCP servers has blown developers’ minds over the past few months, and remote MCP servers have the same potential to open up similar new ways of working with LLMs and agents to a much wider audience, including more everyday consumer use cases.”
The remote MCP connections are missing the piece to reach everyone online. To solve this, Cloudflare aims to bring the MCP servers online to the masses using its platform.
With this move, Cloudflare is positioning itself as a key player in the evolution of MCP, aiming to democratise access to advanced AI agent capabilities.
Your reaction
Discussion
What's your take on this story?
No comments yet — be the first to share your view.