The Model Context Protocol, or MCP, is an open standard that defines how an artificial intelligence assistant or agent connects to an application to read its data and act in it. Introduced by Anthropic at the end of 2024, it is now supported by most major AI players and by many tools.

The principle

  • On one side, an MCP server, published by the application, describes what can be done with it: its tools ("send an email"), its data, and how to use them.
  • On the other, an MCP client: the assistant or agent that connects to it and calls those tools when you ask for something.
  • A server can run on your computer or remotely on the Internet; remotely, the connection usually goes through OAuth.

Why a standard

  • Before MCP, each assistant had its own way of plugging into each tool. With MCP, an application publishes a single server, and every compatible client can use it.
  • For email marketing, this means the same connection works for Claude, ChatGPT, an n8n agent or an AI installed inside the company.

MCP and Mailpro

  • Mailpro publishes a remote MCP server: your assistant reads your account and prepares your emails, campaigns and SMS, with human approval or automatically, as you choose.

Mailpro and AI assistants: an open standard, your account, your rules. Start for free

Previous Article

   

Next Article

You might also be interested in:

The Model Context Protocol, or MCP, is an open standard that defines how an artificial intelligence assistant or agent connects to an application to read its data and act in it. Introduced by Anthropic at the end of 2024, it is no...
A large language model, or LLM, is an artificial intelligence trained on very large amounts of text to understand a request and write an answer. It is the "brain" of AI assistants and AI agents. Hosted models and open models Hos...