mcpbeat Sign in

Google Analytics 4 MCP Server

local only

Google Analytics 4 MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 196 installs a week from pypi. Last commit 9 Sep 2026.

Google Analytics 4 MCP: reports, realtime, funnels, pivots, metadata, admin lists. 17 tools.

Installs per day peak 79 · avg 19 · +57% w/w
a month agotoday
196
Installs / week
pypi · scalably-ga4-mcp
0
Stars
0 open issues
9 Sep 2026
Last commit
from GitHub
MIT
License
Python

Nothing serious here today

Today is the operative word: we check Google Analytics 4 MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add ga4-mcp -e 'GOOGLE_APPLICATION_CREDENTIALS=<GOOGLE_APPLICATION_CREDENTIALS>' -- uvx scalably-ga4-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "ga4-mcp": {
      "command": "uvx",
      "args": [
        "scalably-ga4-mcp"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>"
      }
    }
  }
}
~/.codex/config.toml
[mcp_servers.ga4-mcp]
command = "uvx"
args = ["scalably-ga4-mcp"]
env = { GOOGLE_APPLICATION_CREDENTIALS = "<GOOGLE_APPLICATION_CREDENTIALS>" }
.cursor/mcp.json
{
  "mcpServers": {
    "ga4-mcp": {
      "command": "uvx",
      "args": [
        "scalably-ga4-mcp"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "ga4-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "scalably-ga4-mcp"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>"
      }
    }
  }
}

Put your own value in place of <GOOGLE_APPLICATION_CREDENTIALS> (Path to a Google service-account JSON file with the analytics.readonly scope; add the service account as a Viewer on each GA4 property). The author’s registry entry marks it as required.

Optional settings from the registry entry, left out of the block above: GA4_LOG_LEVEL (Log level, default INFO).

Alternatives to Google Analytics 4 MCP

same job, measured the same way
Google Analytics
by codechap

MCP server for Google Analytics 4 — reports, realtime data, and admin

local only
Ga4
by mharnett

Google Analytics 4 MCP: reports, realtime data, custom dimensions, data streams.

76 installs/wk local only
SEO Tools: Google Analytics 4
by antohins

Google Analytics 4: reports, traffic sources, landing pages, events, realtime (read-only).

16 installs/wk local only
Google Analytics 4
by mindstone

Google Analytics 4 MCP server with reporting, schema discovery, and admin visibility tools

35 installs/wk local only
Google Analytics 4
by getmcpads

Google Analytics 4 MCP server: 27 read tools, no write tools.

37 installs/wk local only
QuerySail: Google Analytics
by querysail

Hosted, read-only Google Analytics 4 MCP: reports, period comparisons, realtime, custom fields.

answering
Ainative Gtm MCP
by ainative-studio

Full Google Ads, Analytics & Tag Manager lifecycle MCP for AI agents — 57 tools.

31 installs/wk local only
Google Analytics 4
by stucchi

Manage GA4 properties, data streams, conversions, and run reports via Admin & Data APIs.

113 installs/wk local only

Google Analytics 4 MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Google Analytics 4 MCP?
Google Analytics 4 MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package scalably-ga4-mcp was installed 196 times last week.
How do I connect Google Analytics 4 MCP?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls scalably-ga4-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use Google Analytics 4 MCP?
The pypi package scalably-ga4-mcp was installed 196 times in the last week. Week over week that is +57%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Google Analytics 4 MCP open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.