What is MCP (Model Context Protocol)?
Anthropic's open standard for connecting AI models to external tools and data sources.
Definition
Model Context Protocol (MCP) is an open protocol developed by Anthropic that standardizes how AI models communicate with external tools, APIs, and data sources. It defines a client-server architecture where MCP servers expose tools (callable functions), resources (readable data), and prompts. Any AI client that speaks MCP can use any MCP-compatible tool without custom integration code.
Example
A GitHub MCP server exposes tools like `github_list_prs` and `github_create_issue`. Any AI that speaks MCP — including Claude, Cursor, or Shogo — can use these tools without each one writing their own GitHub integration.
MCP (Model Context Protocol) vs function calling: What's the difference?
Anthropic's open standard for connecting AI models to external tools and data sources.
Function calling is model-specific. MCP is model-agnostic — one server works with any MCP-compatible client.