io.github.mharnett/gtm-ga4
Quality Score
85
/100
GTM + GA4 MCP: tag management, consent auditing, workspace versioning, reports.
§01 Install
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"gtm-ga4": {
"command": "npx",
"args": [
"-y",
"mcp-gtm-ga4"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "<google_application_credentials>",
"GTM_ACCOUNT_ID": "<gtm_account_id>",
"GTM_CONTAINER_ID": "<gtm_container_id>",
"GA4_PROPERTY_ID": "<ga4_property_id>"
}
}
}
}Cursor (.cursor/mcp.json)
{
"mcpServers": {
"gtm-ga4": {
"command": "npx",
"args": [
"-y",
"mcp-gtm-ga4"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "<google_application_credentials>",
"GTM_ACCOUNT_ID": "<gtm_account_id>",
"GTM_CONTAINER_ID": "<gtm_container_id>",
"GA4_PROPERTY_ID": "<ga4_property_id>"
}
}
}
}Cline (cline_mcp_settings.json)
npx -y mcp-gtm-ga4§02 Environment variables
GOOGLE_APPLICATION_CREDENTIALSrequired
Path to service account JSON credentials file
GTM_ACCOUNT_IDrequired
GTM account ID
GTM_CONTAINER_IDrequired
GTM container ID
GA4_PROPERTY_IDGA4 property ID (numeric)
§03 MCP Quality Score · methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
10
§04 Alternatives in Other
agency.lona/trading
agency.lona/trading
AI-powered trading strategy development: backtesting, market data, and portfolio analysis
ABMeter
ai.abmeter/abmeter
Feature flagging and A/B testing platform with AI-first experimentation workflows.
AdAdvisor MCP Server
ai.adadvisor/mcp-server
Query Meta Ads performance data — accounts, campaigns, ad sets, ads, metrics & settings.