Cross icon
Prefer English?
Prefer English? Switch the website language for a better experience.
Switch language

MCP

Publié le
23/10/2026
Mise a jour le
23/10/2026

TL;DR

Model Context Protocol, an open standard letting an AI connect to external tools and data sources.

MCP (Model Context Protocol) is an open standard that lets an AI connect directly to tools, databases, or external services (Notion, Webflow, Semrush...) in a standardized way, rather than through integrations built case by case. It turns a language model into an agent capable of acting concretely on real systems. Mazette.co uses it in particular to operate Webflow, Notion, or Semrush directly from Claude.

Code

Copier le code
Copy icon Check icon

Our other definitions

AI Agent

An AI system able to carry out tasks autonomously using tools and making decisions.

Lire la définition
Arrow right icon

API

An interface that lets two pieces of software communicate and exchange data.

Lire la définition
Arrow right icon

LLM

Large Language Model, an AI model trained on huge volumes of text to understand and generate language.

Lire la définition
Arrow right icon

n8n

An open-source workflow automation tool that connects different applications together.

Lire la définition
Arrow right icon
Mazette.co
/
Glossary
/
MCP

Illuminate your ideas with our expertise

Start your project now

Over 180 companies have already stepped out of the shadows with us.

Frequently asked questions

What is MCP in AI?

Icon chevron

MCP, the Model Context Protocol, is an open standard introduced by Anthropic in 2024. It gives AI apps one common way to connect to tools and data sources, a bit like USB-C for AI, instead of a custom integration for every service.

What are some examples of MCP servers?

Icon chevron

Servers exist for tools like Notion, GitHub, Slack, Google Drive and Webflow, plus local ones for files and databases such as PostgreSQL. Each server exposes a set of tools that an AI client can discover and call.