Google Analytics 4 runs on your own machine — the client starts it, so there is no endpoint to ping. 64 installs a week from npm. Last commit 2 Nov 2026.
Google Analytics 4 MCP server with reporting, schema discovery, and admin visibility tools
We read the source, 22 h ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
fs.writeFileSync(outFd, pdfBuffer);
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const fullPath = path.join(stagingDir, filename);
const child = spawn(process.execPath, [script], {
if (isUnder(resolvedAbs, sshDir)) return { hit: true, reason: '~/.ssh/** is sensitive' };
<script src="https://appsforoffice.microsoft.com/lib/1.1/hosted/office.js"></script>
const entries = fs.readdirSync(workspacePath, { withFileTypes: true });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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.
claude mcp add mcp-server-google-analytics -e 'GOOGLE_APPLICATION_CREDENTIALS=<GOOGLE_APPLICATION_CREDENTIALS>' -- npx -y @mindstone/mcp-server-google-analytics
{
"mcpServers": {
"mcp-server-google-analytics": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-google-analytics"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>"
}
}
}
}
[mcp_servers.mcp-server-google-analytics]
command = "npx"
args = ["-y", "@mindstone/mcp-server-google-analytics"]
env = { GOOGLE_APPLICATION_CREDENTIALS = "<GOOGLE_APPLICATION_CREDENTIALS>" }
{
"mcpServers": {
"mcp-server-google-analytics": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-google-analytics"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>"
}
}
}
}
{
"servers": {
"mcp-server-google-analytics": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-google-analytics"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>"
}
}
}
}
Put your own value in place of
<GOOGLE_APPLICATION_CREDENTIALS> (Absolute path to ADC or service-account JSON file).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
GA4_PROPERTY_ID (Default GA4 property ID (e.g. 123456789)).
MCP server for Google Analytics 4 — reports, realtime data, and admin
Google Analytics 4 MCP server: 27 read tools, no write tools.
Google Analytics 4 MCP: reports, realtime, funnels, pivots, metadata, admin lists. 17 tools.
Query selected Google and Bing analytics, search, and advertising reports through MCP.
AI visibility MCP server: how 7 AI engines cite your brand daily, with Google Search Console.
MCP stdio server for analyzing YouTube videos with Google Gemini
Manage GA4 properties, data streams, conversions, and run reports via Admin & Data APIs.
Read-only Google Analytics 4 MCP server for AI assistants.
Answers built from our own checks of this server.