What is the Model Context Protocol (MCP)?
An open protocol, introduced by Anthropic in November 2024, that lets AI applications connect to external tools and data through a standard interface.
Before MCP, every AI app needed its own plug-in format for every service. MCP defines one: a server describes its tools, resources and prompts, and any MCP-capable app can use them. Messages are JSON-RPC 2.0, carried over stdio for local servers or Streamable HTTP for remote ones.
The specification is versioned by date (for example 2025-06-18); client and server agree on a version during the initialize handshake.
Sources
Related terms
- MCP serverA program that exposes tools, resources or prompts to AI applications over the Model Context Protocol.
- MCP client and hostThe host is the AI application (an IDE, a desktop chat app, a CLI agent); inside it, one MCP client holds the connection to each MCP server.
- Tool call (tools/list, tools/call)How an AI model uses an MCP tool: the client lists the server's tools with tools/list, the model picks one, and the client runs it with tools/call and returns the result to the model.
- JSON-RPC 2.0The small remote-procedure-call format MCP uses: requests with jsonrpc, id, method and params; responses with the same id and either result or error.