Overview of Model Context Protocol (MCP) server

The Model Context Protocol (MCP) is a standard that lets AI apps talk to tools like APIs, databases, and analytics platforms in a consistent way. It makes it possible for AI models to understand and perform tasks like “create a new Google Tag Manager container” or “list tags” without needing code or manual API calls.

The MCP server is Stape’s proprietary engine behind this. It connects your AI assistant (like Claude or ChatGPT) to Google Tag Manager (GTM) or server-side containers within Stape. The MCP server takes your plain-language requests and translates them into real actions on these platforms.

Benefits of the MCP server

Managing and configuring GTM containers or server-side tracking often requires dealing with APIs, code, or platforms like Google Cloud. To a non-developer, that’s all quite complicated.  And if you’re an agency or freelancer offering SST setup services, it can be quite repetitive and time-consuming.

With the MCP server, you can skip that. You type a request in an AI app (like “Create a GTM tag that fires on pageview”), and it just works. No coding, no dev help, and no documentation hunting.

Here are just a few examples of what you can do, using only plain text, thanks to the MCP server:

• Add or update GTM tags, triggers, and variables.
• Manage GTM containers or server containers on Stape.
• List or change user permissions.
• And much more!

This results in faster workflows, fewer bottlenecks, and more control over your analytics and advertising, without needing technical skills or routine tinkering.

How to set up the MCP server

There are two ways you can use an MCP server:

• For Stape: a simple way to manage containers on Stape via AI.
• For GTM: another way to manage containers in your account, or tags, triggers, and variables in your GTM containers.