AUTOMATIONSWITCH

Google Analytics MCP

by Google

Official Google MCP server for Google Analytics 4. Query reports, dimensions, metrics, custom audiences, and admin entities through MCP. 1,981 GitHub stars and 5 commits on main in the last 30 days. Apache-2.0.

1,981·7 tools·Released DEC 2025·Apache-2.0
pip install google-analytics-mcp
Share:

Official Google MCP server for Google Analytics 4. Query reports, dimensions, metrics, custom audiences, and admin entities through MCP. 1,981 GitHub stars and 5 commits on main in the last 30 days. Apache-2.0. Top star count in this batch.

Reviewed by M. Nouriel · MAY 2026

INSTALL THIS SERVER

Requires authenticationOAuth 2.0 user credentials or service account JSON key. Recommended path for agent deployments is a dedicated service account with read-only Analytics access.
{ "mcpServers": { "google-analytics": { "command": "python", "args": [ "-m", "google_analytics_mcp" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json" } } } }
PrereqRequires GOOGLE_APPLICATION_CREDENTIALS pointing to a service account JSON with Google Analytics read scope. PyPI: `google-analytics-mcp`. Service account must be granted Viewer access on the GA4 properties. Path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).
{ "mcpServers": { "google-analytics": { "command": "python", "args": [ "-m", "google_analytics_mcp" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json" } } } }
{ "mcpServers": { "google-analytics": { "command": "python", "args": [ "-m", "google_analytics_mcp" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json" } } } }
{ "mcpServers": { "google-analytics": { "command": "python", "args": [ "-m", "google_analytics_mcp" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json" } } } }
{ "mcpServers": { "google-analytics": { "command": "python", "args": [ "-m", "google_analytics_mcp" ], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json" } } } }

7 TOOLS AVAILABLE

run_report
Run a GA4 report with metrics, dimensions, date range, filters
Read
get_metadata
List available dimensions and metrics for a property
Read
list_accounts
List GA accounts the credential can see
Read
list_properties
List GA4 properties for an account
Read
list_audiences
List custom audiences on a property
Read
get_property
Get a property configuration
Read

OUR ASSESSMENT

Strengths
  • 1,981 GitHub stars and Apache-2.0 licence.
  • Official Google maintenance.
  • 5 commits on main in the last 30 days.
  • Tool surface covers reporting (run_report) plus admin (accounts, properties, audiences, data streams).
  • GA4-native: focuses on the current Analytics platform.
  • OAuth and service account authentication options.
Weaknesses
  • Google Analytics OAuth credentials grant scoped read access; service accounts are the recommended path for agent deployments.
  • GA4 API quotas apply per project; high-volume agents can exhaust quota.
  • Reporting tool input requires GA4 dimension and metric IDs; agents trained on Universal Analytics names may produce queries that need re-mapping.
Security Notes

GA OAuth tokens or service-account JSON keys grant read access to the Google Analytics properties scoped at credential creation. Use a dedicated service account with read-only Analytics access for production agents. The MCP forwards all queries to the Google Analytics API; results contain user-level data when the property uses User-ID; treat the result stream as sensitive.

Best For

Teams running Google Analytics 4 for web analytics who want agents to query reports inside the editor; analytics workflows where the agent retrieves dimensions, metrics, audiences, or property configuration; production deployments using service-account authentication for headless agents.

TECHNICAL DETAILS

Language
python
Transport
stdio
Clients
Claude DesktopClaude CodeCursorVS CodeWindsurf
License
Apache-2.0
npm
google-analytics-mcp
Last Release
google-analytics-mcp (PyPI latest)MAY 3, 2026
First Released
DEC 1, 2025

ADOPTION METRICS

// GitHub Stars
1,981

// Reading this1,981 stars on the googleanalytics/google-analytics-mcp repo. 5 commits on main in the last 30 days. Top star count in this batch.

// Popularity Rank
#1
Globally · #1 in Data / Analytics

// Reading thisFirst-ranked in this batch on combined star count and Google official-vendor signal.

SOURCES & VERIFICATION

We don't take any single directory's word for it. Before scoring, we cross-reference 5 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.

01
Discovered
Manual submission
First indexed MAY 3, 2026
02
Cross-referenced
5 directories
PulseMCP, MCP.so, Glama, Smithery, Official MCP Registry
03
Verified against
Claude Desktop, Cursor, VS Code
Installed and tested across clients
04
Last re-checked
MAY 3, 2026
Weekly re-verification
// How other directories see it

The same server, 5 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.

SourceTheir ratingTheir star countTheir downloadsLast synced
AutomationSwitch This page4.6editorial1,981MAY 3, 2026
PulseMCP— unratedunavailableunavailableMAY 3, 2026
MCP.so— unratedunavailableunavailableMAY 3, 2026
Glama— unratedunavailableunavailableMAY 3, 2026
Smithery— unratedunavailableunavailableMAY 3, 2026
Official MCP Registry— unratedunavailableunavailableMAY 3, 2026

// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.

// Get in touch

DISCUSS YOUR
MCP REQUIREMENTS.

Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.

Discuss Your MCP Requirements →