The short answer
Google publishes an official Google Analytics MCP server. It is open source, marked experimental, and runs on your own computer with a Google Cloud project and your own credentials. ChatGPT and Claude on the web connect to remote MCP servers over the internet, so a server running on your computer is not something you paste into them. SAR Intelligence hosts that same official server, so there is nothing to install: you sign in with Google, choose one GA4 property and add one address.
For the steps and everything a hosted GA4 connection reads, see Google Analytics 4 with ChatGPT and Claude.
Key points
- Google's official server lives on GitHub as googleanalytics/google-analytics-mcp. It is open source under the Apache 2.0 license, and its README marks it experimental.
- It runs locally and needs pipx, a Google Cloud project with the Analytics Admin API and Analytics Data API turned on, and Application Default Credentials with the analytics.readonly scope.
- ChatGPT developer mode adds a remote MCP server, and Claude reaches a custom connector's server from Anthropic's cloud, over the public internet.
- SAR Intelligence runs Google's official server itself, without changing its code. You sign in with Google, choose one GA4 property and add one address to ChatGPT or Claude.
- Either way the server only reads. Google says it cannot change your Analytics settings, and SAR connects with the read-only analytics.readonly scope.
Running Google's server yourself or having it hosted
| What differs | Run it yourself | Hosted by SAR Intelligence |
|---|---|---|
| The server | Google's official google-analytics-mcp | The same server, run by SAR without changes to its code |
| Where it runs | On your computer, started by the AI app that uses it | On SAR's servers, at one web address |
| What you set up | pipx, a Google Cloud project, two APIs turned on and Application Default Credentials | Sign in with Google and choose one GA4 property |
| AI apps in its instructions | Gemini CLI, Gemini Code Assist and Claude Code | ChatGPT and Claude, as a custom connector |
| Which properties it reaches | Any account and property the Google credentials can open | The one GA4 property you choose, for one organization |
| Access | Read requests only, with analytics.readonly | Read-only, with analytics.readonly |
| Status | Open source (Apache 2.0), marked experimental | Invite-only pilot |
Google's official Google Analytics MCP server
Google's developer documentation presents the Google Analytics MCP server as a way to connect your Analytics data to an LLM such as Gemini, to chat with your data or build your own agents. The code lives in the googleanalytics organization on GitHub under the Apache 2.0 license, and the README title marks it experimental.
The server uses the Google Analytics Admin API and the Google Analytics Data API. Google notes that it handles read requests only and cannot edit your Google Analytics configuration or settings. The README lists these tools:
- get_account_summaries: the user's Google Analytics accounts and properties.
- get_property_details and list_google_ads_links: details of one property and its links to Google Ads accounts.
- run_report and run_funnel_report: reports and funnel reports through the Data API.
- get_custom_dimensions_and_metrics: a property's custom dimensions and metrics.
- run_realtime_report: realtime reports.
What it takes to run it
The server runs on your own computer. The README gives these steps:
- Install pipx. The package needs Python 3.10 or later.
- Turn on the Google Analytics Admin API and Google Analytics Data API in a Google Cloud project.
- Set up Application Default Credentials for a user with access to your Google Analytics accounts or properties, with the analytics.readonly scope, for example through gcloud and an OAuth client.
- Register the server in your AI app's settings. The README shows Gemini CLI, Gemini Code Assist and Claude Code, which start it with pipx on the same computer.
Why a local server does not go into ChatGPT or Claude
For ChatGPT developer mode, OpenAI describes creating an app for your remote MCP server, over SSE or streaming HTTP. Anthropic writes that Claude connects to a custom connector's server from Anthropic's cloud rather than from your device, in every Claude app. That server must be reachable over the public internet.
So a server running on your computer is not an address you paste into ChatGPT or Claude on the web. Claude Desktop can run local MCP servers from its configuration file, but Anthropic describes that as a separate mechanism that claude.ai does not have.
How SAR Intelligence hosts it
SAR Intelligence runs Google's official Google Analytics MCP server on its own servers, without changing its code, and adds what a hosted service needs: Google sign-in, one property per connection, organizations and a way to revoke access.
It passes the server's read tools to ChatGPT or Claude through an allowlist, so a tool added in a later version of Google's server stays hidden until SAR has reviewed it. You install nothing and create no Google Cloud project. During the pilot, SAR Soft sets up your first connection with you on a short call.
- Sign in with Google, allow read-only access (analytics.readonly) and choose one GA4 property.
- Add https://mcp.sar-soft.com/mcp as a custom connector in ChatGPT (with developer mode turned on) or Claude.
- Sign in to SAR when asked and authorize one organization. The connector reaches no other organization.
- Revoke the AI app in the SAR Intelligence app, and it takes effect within about a minute.
When each fits
Running Google's server yourself fits a developer who is comfortable with Google Cloud and credentials, and who works in a local AI app such as Gemini CLI or Claude Code.
Having it hosted fits a business owner or agency working in ChatGPT or Claude who wants to pick a property without running anything. An agency creates one organization per client.
Either way, the AI app writes the answer, and it can be wrong or incomplete. Check the numbers that matter in GA4.
Questions to try
- How much traffic did we get in the last 30 days, compared with the 30 before?Sources: Google Analytics
- Which landing pages brought in the most visitors this month?Sources: Google Analytics
- Where did our visitors come from last week?Sources: Google Analytics
- Which pages get plenty of search impressions but little actual traffic?Sources: Search Console · Google Analytics
Questions people ask
Is Google's Google Analytics MCP server official?
Yes. It lives in the googleanalytics organization on GitHub, and Google's Analytics developer documentation links to it. Its README marks it experimental.
Can I add Google's server to ChatGPT or Claude on the web?
Not the way its README runs it, on your computer. ChatGPT and Claude on the web connect to remote servers over the internet. Claude Desktop runs local servers from its configuration file, which is a separate mechanism from custom connectors.
Does SAR Intelligence use Google's official server?
Yes. SAR runs Google's official Google Analytics MCP server without changing its code, and hosts it where ChatGPT and Claude on the web can reach it. SAR adds Google sign-in, one property per connection, organizations and revoking access.
Which ChatGPT or Claude plan does SAR Intelligence need?
You add SAR as a custom connector (in ChatGPT, with developer mode turned on). The plans that can do this are listed below.
- ChatGPTOn a Plus, Pro, Business, Enterprise or Edu plan, on the web, with developer mode turned on.OpenAI's guide
- ClaudeOn any plan. Free allows one custom connector, and on Team and Enterprise an owner adds it first.Anthropic's guide
Can it change my GA4 settings?
No. Google says its server handles read requests only, whoever runs it. SAR connects with analytics.readonly and gives the AI app read tools only.