How MCP connects AI apps to tools and data
Model Context Protocol (MCP) is described as an open standard for connecting AI applications with tools, data and prompts through servers. An app first asks a server for its capabilities, presents the available tools to the model, and relays tool calls and results between the model and the server. JSON-RPC serves as the message envelope, while MCP defines methods, capability negotiation, transports and authentication.
The explainer provides a concrete account of how MCP coordinates AI applications, models and servers, including capability discovery, tool calls, result handling and the protocol’s core components.
Model Context Protocol
What is MCP?
An open standard for connecting AI apps to the tools and data they use. A server says what it can do, the app shows that to the model, and when the model wants something the app calls the server and hands the result back.
Host the AI app you use: Claude, Cursor, ChatGPT, an agent Server a small program exposing tools, data or prompts Model decides what to use; never talks to a server directly Not REST JSON-RPC over stdin/stdout or one HTTP endpoint, and servers can talk back Not just JSON-RPC JSON-RPC is the envelope. MCP defines what goes in it: the methods, capability negotiation, transports and auth or jump to Tools · the spec time machine · Break it
Step 1 of 5
Connect