Why it matters
AI assistants are becoming a real interface to software: people ask a question, and the assistant does the work behind the scenes. Before MCP, every connection between an assistant and a tool required custom development. With MCP, any assistant that speaks the protocol can work with any service that exposes it, which is why it has spread so quickly across the AI ecosystem.
How it works
A service publishes an MCP server that describes a set of tools: typed actions such as "list products", "create an article", or "update a price". An AI assistant connects to that server, discovers the available tools, and calls them when a conversation requires it, using the results to ground its answers. The user stays in control: the connection is authorized explicitly, and the server defines exactly what the assistant is allowed to see and do. Nothing happens outside the tools the server chooses to expose.
How GoodBarber relates to this
Every GoodBarber app comes with its own MCP server. You can connect Claude, ChatGPT, or any MCP-compatible assistant to your app's back office and manage content, products, or settings by simply asking. Connect your app to an AI assistant to see it in action, or follow the complete MCP guide.
Frequently asked questions
- What does MCP stand for?
- MCP stands for Model Context Protocol, an open standard introduced by Anthropic in 2024 and since adopted by the major AI assistants. It defines a common way for assistants to discover and call the capabilities a service chooses to expose.
- Do I need to be a developer to use MCP?
- No. When a platform provides a ready-made MCP server, connecting an assistant is a configuration step, not a coding project. In GoodBarber, you connect your assistant to your app with a URL, without writing any code.
Design