Query Analytics property information and reports through the experimental first-party MCP server.
Google Analytics MCP is an experimental local server published by the Google Analytics project. It connects an assistant to the Analytics Admin and Data APIs for property information and reporting.
Start by identifying the property and date range. Then name the dimensions and metrics you want: traffic by channel, an event trend or a funnel stage. Ask the assistant to preserve those choices with the result so another person can reproduce the report.
The documented setup uses Python with pipx and Google Application Default Credentials. Enable the Admin and Data APIs in the selected Cloud project and use credentials with access to the intended Analytics property. The README requires the analytics read-only scope.
Check property time zone, filters, attribution and metric definitions before comparing totals with a dashboard. Realtime reports and historical reports answer different questions. An assistant can summarize the returned data, but the report settings determine what the numbers mean.
The repository labels this integration experimental. Test one property and a small report before using it for routine analysis. Keep credential files outside source control and confirm that the account can read only the resources your workflow needs.
Explore analytics MCP integrations or browse the official server directory.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| get_account_summaries | List available analytics accounts and properties. |
| get_property_details | Inspect the selected property. |
| list_google_ads_links | Inspect linked advertising accounts. |
| run_report | Query a core Analytics Data API report. |
| run_funnel_report | Query a funnel report. |
| get_custom_dimensions_and_metrics | Inspect a property's custom reporting fields. |
| run_realtime_report | Query a realtime report. |
{
"mcpServers": {
"analytics-mcp": {
"command": "pipx",
"args": [
"run",
"analytics-mcp"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/absolute/path/to/credentials.json",
"GOOGLE_PROJECT_ID": "your-project-id"
}
}
}
}Configure ADC and enable both Analytics APIs first. Replace the credential path and project ID with your own values.
Python, pipx, enabled Analytics Admin and Data APIs, Application Default Credentials and property access.
| Variable | Description | Required |
|---|---|---|
| GOOGLE_APPLICATION_CREDENTIALS | Path to the configured Application Default Credentials JSON file. | Yes |
| GOOGLE_PROJECT_ID | Cloud project ID used in the documented client configuration. | Optional |
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Facilitates interaction with the PyTorch HUD API, providing access to CI/CD data, job logs, and analytics.
MCP server for 1C:Enterprise (1С) over OData. Ask your accounting database in natural language — debtors, sales, taxes, cash flow — from any MCP
Your AI marketing analyst, connected to live data. 75 MCP tools across Google Ads, Meta Ads, GA4, Search Console, Shopify, Stripe and WordPress — read, analyze, manage, and monitor.
Draft, schedule and publish LinkedIn posts, reply to comments and read analytics via 2pr.io.
Read Accredible credentials, groups, designs, analytics, skills; issue one credential as a draft.