# QuerySail: Google Analytics MCP [Health: Active]

**Category:** 🎯 Marketing  
**Repository:** https://github.com/querysail/querysail-ga4  
**GitHub Stars:** 0  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/querysail-google-analytics-mcp

## Description
Hosted, read-only Google Analytics 4 MCP server. Connect your Google account and query traffic, engagement, conversions, realtime activity, properties, dimensions and metrics using natural language.

## Tools
Capabilities this server exposes over MCP:

- **list_properties** — Lists the Google Analytics 4 properties your connected Google accounts can read, with exact property IDs and their Analytics accounts.
- **list_fields** — Lists the dimensions and metrics a property can report on, including its custom dimensions, custom metrics and key events.
- **run_report** — Users, sessions, views, engagement, events, key events, revenue and any other Data API metric, broken down by date, channel, source/medium, landing page, page, country, device, event and more, with filters.
- **compare_report** — Compares two periods (previous period, same weekdays a year earlier, or custom dates) and lists the channels, sources, pages or countries that gained or lost the most.
- **run_realtime_report** — Active users, views and events in the last 30 minutes, by country, city, device, page or event.

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: high). Install path detected from listing signals. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "querysail-google-analytics-mcp": {
    "url": "https://mcp.querysail.com/ga4/mcp"
  }
}
```

## Documentation

## What QuerySail: Google Analytics MCP MCP server does

QuerySail: Google Analytics MCP MCP server gives MCP-compatible AI clients read-only access to Google Analytics 4 data. It connects to the Google account authorized through QuerySail and exposes property discovery, schema discovery, historical reporting, period comparisons, and realtime reporting as MCP tools.

The service can answer questions about users, sessions, views, engagement, events, key events, revenue, acquisition channels, source and medium, landing pages, countries, devices, and other GA4 dimensions and metrics. Reports can include filters, while comparison queries can identify which channels, sources, pages, or countries increased or decreased between two periods.

It does not modify Google Analytics. Properties, data streams, key events, audiences, and other settings remain unchanged because every exposed tool is read-only. Universal Analytics properties are not supported.

## How it works

The hosted endpoint is `https://mcp.querysail.com/ga4/mcp`. It uses Streamable HTTP and OAuth 2.1 with dynamic client registration, so compatible clients connect to the URL rather than launching a local server. After the first sign-in, the client can use the connected Google Analytics account through QuerySail.

The `list_properties` tool shows the GA4 properties available to the connected Google accounts and includes their exact property IDs and Analytics accounts. `list_fields` helps identify the dimensions and metrics supported by a selected property, including custom dimensions, custom metrics, and key events. The reporting tools then retrieve data from Google when requested.

Historical reports may be cached for up to 15 minutes; realtime reports are not cached. Google can apply sampling or thresholding to some results, and its flags are passed through to the assistant. Google’s per-property API quotas also apply.

## Setup and configuration

Create a QuerySail account and connect Google Analytics under **Account → Connections**. The connection uses the `analytics.readonly` scope, which is separate from Search Console access. QuerySail requires no Google Cloud project and no API key pasted by the user.

Add the hosted URL as an HTTP MCP server in a supported client. Claude Code and Codex provide command-line setup and browser-based login. Claude Desktop, Cursor, and VS Code can use their connector or MCP configuration interfaces. ChatGPT can connect through Developer mode and its plugins connection flow. Clients that only run local commands can use the `mcp-remote` bridge with Node.js.

QuerySail: Google Analytics MCP MCP server requires a QuerySail account with Google Analytics connected. Google credentials are encrypted at rest, and users can disconnect Google, hide properties, or delete the QuerySail account.

## Tools and capabilities

- `list_properties`: Finds readable GA4 properties and their property IDs.
- `list_fields`: Lists reportable dimensions, metrics, custom fields, and key events for a property.
- `run_report`: Queries historical GA4 metrics with dimensions and filters.
- `compare_report`: Compares a previous period, matching weekdays from the prior year, or custom date ranges.
- `run_realtime_report`: Reports active users, views, and events from the last 30 minutes by supported dimensions such as country, city, device, page, or event.

## Limitations and notes

The repository contains listing files, client configurations, and a Claude Code plugin; the hosted service source is not published there. The service is read-only and depends on Google Analytics permissions, API quotas, and any Google-applied sampling or thresholding. The repository files are MIT licensed, while use of the hosted service is governed by QuerySail’s terms. Pricing information in the supplied material describes a seven-day trial followed by $8 per month, with the GA4 service included in the same plan as QuerySail for Google Search Console.

_Full upstream README: https://allmcps.com/mcp/querysail-google-analytics-mcp/readme_