What is the Model Context Protocol?
A developer's guide. Five minutes from "I've heard of MCP" to your first server installed.
The 30-second version
MCP is to AI assistants what USB is to peripherals - a standard way to plug capability into a host without rewriting the host.
The Model Context Protocol (MCP) is an open standard from Anthropic that lets AI assistants connect to external tools, APIs, and data. An MCP server exposes a set of tools - a GitHub server exposes tools for reading repos and creating PRs. An MCP client is the AI tool that calls those tools - Claude, Cursor, or VS Code with Copilot.
Anthropic released the spec in late 2024. By 2026 every major AI coding tool speaks it.
install_serverthrough 1ServerYour AI client speaks to 1Server; 1Server speaks to every server you install.
What problem does MCP solve?
Before MCP, every AI tool had its own plugin system. Building a Slack integration for Claude meant writing it for Claude. Building Slack for Cursor meant writing it again.
MCP fixes that. One server (e.g. slack-mcp-server) works in every MCP-compatible client. Build once, run everywhere.
Server. Client. 1Server.
Three pieces. Worth keeping straight.
Server
A small process that exposes tools. Read a file, query a database, hit an API. The GitHub MCP server, the Postgres MCP server, the Slack MCP server.
Client
The AI tool that calls those tools. Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI, ChatGPT. The client speaks MCP and routes tool calls to servers.
1Server
A single MCP server that hosts every server you install. One config replaces many; new servers go live without restarting your client.
Which tools speak MCP?
Every major AI coding tool by 2026.
Five minutes. One config snippet. Every client you already use.
Pick a server, paste the snippet, restart your AI client once.