Open protocol that lets LLMs connect to tools, data sources and apps through a standard interface.
2 min readupdated 2026-06-21
/ quick answer
The Model Context Protocol (MCP) is an open standard for exposing tools, files and APIs to AI models. Instead of bespoke plugins per vendor, an MCP server describes its capabilities and any compatible client (Claude, Cursor, IDE agents, custom apps) can call them with a shared schema — like USB for AI tools.
The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in late 2024 and now supported by every major AI vendor, that lets language models talk to tools, files and APIs through a single shared interface. Before MCP, every AI product had to build custom plugin systems and every tool vendor had to write a separate integration for ChatGPT, Claude, Cursor and each new client. MCP replaces that N-times-M problem with one protocol: a tool provider ships an MCP server describing what it can do, and any MCP-compatible client can discover and call it. In practice that means the same GitHub, Postgres, Notion or internal-API server works in Claude Desktop, Cursor, VS Code, Zed and custom agent runtimes — often with zero client-side code changes. MCP is quickly becoming the USB-C moment for AI: a boring standard whose value is that everything speaks it.
Definition
The Model Context Protocol (MCP) is an open standard for exposing tools, files and APIs to AI models. Instead of bespoke plugins per vendor, an MCP server describes its capabilities and any compatible client (Claude, Cursor, IDE agents, custom apps) can call them with a shared schema — like USB for AI tools.
Example
An MCP server wraps your internal Postgres and ticketing system; Claude Desktop adds it as a connector and can now answer questions and create tickets without custom integration code.
Model Context Protocol. It is an open standard for exposing tools, resources and prompt templates to AI models over a JSON-RPC channel.
Who created MCP?
Anthropic released the specification in November 2024. OpenAI, Google, Microsoft, Cursor and most agent frameworks have since adopted it.
How is MCP different from an OpenAI plugin or a Claude tool call?
Plugins and tool calls are proprietary and tied to one vendor. MCP is a shared protocol: one MCP server works with Claude, ChatGPT, Cursor, VS Code, custom agents and anything else that speaks MCP.
Do I need to run my own MCP server?
Only if you want to expose your own data or tools. Public MCP servers already exist for GitHub, Postgres, Notion, filesystems and hundreds of SaaS tools.
Is MCP secure for internal data?
MCP transport is transport-agnostic (stdio, HTTP, SSE) and defers auth to the transport. Self-hosting a server behind your VPN with scoped credentials keeps data inside your perimeter.