Google has launched an open-source Mannequin Context Protocol (MCP) server that allows you to analyze Google Analytics knowledge utilizing massive language fashions like Gemini.
Introduced by Matt Landers, Head of Developer Relations for Google Analytics, the software serves as a bridge between LLMs and analytics knowledge.
As an alternative of navigating conventional report interfaces, you possibly can ask questions in plain English and obtain responses immediately.
A Shift From Conventional Reviews
The MCP server provides an alternative choice to digging by means of menus or configuring stories manually. You’ll be able to kind queries like “What number of customers did I’ve yesterday?” and get the reply you want.
Screenshot from: YouTube.com/GoogleAnalytics, July 2025.In a demo, Landers used the Gemini CLI to retrieve analytics knowledge. The CLI, or Command Line Interface, is a straightforward text-based software you run in a terminal window.
As an alternative of clicking by means of menus or dashboards, you kind out questions or instructions, and the system responds in plain language. It’s like chatting with Gemini, however out of your desktop or laptop computer terminal.
When requested about consumer counts from the day past, the system returned the right complete. It additionally dealt with follow-up questions, displaying the way it can refine queries based mostly on context with out requiring extra technical setup.
You’ll be able to watch the complete demo within the video under:
What You Can Do With It
The server makes use of the Google Analytics Admin API and Knowledge API to help a variety of capabilities.
In line with the venture documentation, you possibly can:
- Retrieve account and property info
- Run core and real-time stories
- Entry customary and customized dimensions and metrics
- Get hyperlinks to linked Google Advertisements accounts
- Obtain hints for setting date ranges and filters
To set it up, you’ll want Python, entry to a Google Cloud venture with particular APIs enabled, and Utility Default Credentials that embody read-only entry to your Google Analytics account.
Actual-World Use Circumstances
The server is particularly useful in additional superior situations.
Within the demo, Landers requested for a report on top-selling merchandise over the previous month. The system returned outcomes sorted by merchandise income, then re-sorted them by models offered after a follow-up immediate.
Screenshot from: YouTube.com/GoogleAnalytics, July 2025.Later, he entered a hypothetical state of affairs: a $5,000 month-to-month advertising funds and a purpose to extend income.
The system generated a number of stories, which revealed that direct and natural search had pushed over $419,000 in income. It then steered a plan with particular funds allocations throughout Google Advertisements, paid social, and e mail advertising, every backed by efficiency knowledge.
Screenshot from: YouTube.com/GoogleAnalytics, July 2025.How To Set It Up
You’ll be able to set up the server from GitHub utilizing a software referred to as pipx, which helps you to run Python-based functions in remoted environments. As soon as put in, you’ll join it to Gemini CLI by including the server to your Gemini settings file.
Setup steps embody:
- Enabling the mandatory Google APIs in your Cloud venture
- Configuring Utility Default Credentials with read-only entry to your Google Analytics account
- (Non-compulsory) Setting surroundings variables to handle credentials extra constantly throughout completely different environments
The server works with any MCP-compatible consumer, however Google highlights full help for Gemini CLI.
That can assist you get began, the documentation consists of pattern prompts for duties like checking property stats, exploring consumer conduct, or analyzing efficiency traits.
Trying Forward
Google says it’s persevering with to develop the venture and is encouraging suggestions by means of GitHub and Discord.
Whereas it’s nonetheless experimental, the MCP server offers you a hands-on strategy to discover what pure language analytics would possibly appear like sooner or later.
In case you’re on a advertising workforce, this might make it easier to get solutions quicker, with out requiring dashboards or customized stories. And if you happen to’re a developer, you would possibly discover methods to construct instruments that automate components of your workflow or make analytics extra accessible to others.
The complete setup information, supply code, and updates can be found on the Google Analytics MCP GitHub repository.
Featured Picture: Mijansk786/Shutterstock
