MCP (Model Context Protocol) standardises how AI models talk to the world. Instead of each LLM having its own plugin API, MCP provides a universal tool-discovery and invocation protocol. An MCP server exposes resources, tools, and prompts. An MCP client (like Claude, Cursor, or your custom agent) discovers them at runtime. The result: write a tool once, use it everywhere.
The 5-Mode Loop
5 of 5 modes available
Read · See · Animate · Test · Build
Before this, understand: agentic workflows