Model Context Protocol (MCP)

The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in late 2024, that defines a common way to connect AI ✕ Artificial intelligence is a computer system’s ability to perform tasks we associate with human intelligence, such as understanding language, recognizing images or making decisions. More in the glossary → models to external tools, data sources and applications. Instead of building a custom integration for every service, MCP acts as a universal connector —it is often compared to a USB-C port for AI—: any compatible assistant can talk to any tool that exposes an MCP server ✕ A server is a powerful computer that provides data or services to other devices — for example serving a website or storing your cloud files. More in the glossary → . That lets a language model, for example, check your calendar, query a database ✕ A database stores a site’s content —posts, pages, comments— in an organized way so it can be retrieved instantly. WordPress uses MySQL or MariaDB. More in the glossary → or read files, always with controlled permissions. It is a key building block for AI agents ✕ An AI agent does not just answer; it carries out multi-step tasks on its own: it searches, uses tools and acts to reach a goal. More in the glossary → , which need to act on the real world rather than just generate text. Being open, different vendors can adopt it, which reduces lock-in to a single provider.