Skip to main content

Overview

What is MCP​

MCP is an open protocol that standardizes how AI applications provide context to large language models (LLMs). Think of MCP as the USB-C interface for AI applications. Just as USB-C provides a standardized way for devices to connect various peripherals and accessories, MCP offers a standardized way for AI models to connect different data sources and tools.

The core of MCP adopts a Client-Server architecture, where a single application can connect to multiple MCP Servers.

As long as AI applications implement MCP, they can connect to any MCP Server to extend their capabilities. After joining an MCP Server, the tool invocation process is as follows:

In this way, MCP achieves:

  1. Plug and Play: AI applications only need to implement the MCP protocol to access a rich ecosystem of third-party tools.
  2. Standardization: All tools follow a unified description format and invocation method.
  3. Decoupling Tools and Applications: Tool providers can independently develop and maintain tools without needing to understand the internal implementation of AI applications.
  4. Resource Sharing: Tools developed once can be reused by multiple AI applications.

Cloud Development provides comprehensive MCP support: