mcpField
V
Vosik Signals Google Analytics 4

Vosik Signals Google Analytics 4

Remote
vosiksignals.winData & Analytics0Updated 3w ago
RepositoryVisit website

About Vosik Signals Google Analytics 4

Vosik Signals Google Analytics 4 is a hosted, read-only MCP server for AI assistants that need to explore GA4 data. It supports account and property discovery, date-range reports, and conversational analysis; the server source is not published.

Key features

  1. 01Discover accessible Google Analytics accounts and properties
  2. 02Query GA4 reports by date range
  3. 03Analyze traffic, users, and acquisition metrics
  4. 04Explore results through an MCP-compatible AI client

Use cases

  1. 01List accessible GA4 properties
  2. 02Compare sessions across date ranges
  3. 03Review acquisition sources and user activity

MCP support

Exposes read-only Google Analytics 4 account discovery and reporting to MCP clients through a hosted endpoint. Connection uses remote Streamable HTTP and Google OAuth.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://ga4.vosiksignals.win/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Vosik Signals — Google Analytics 4 MCP

Part of Vosik Signals — hosted Google Analytics 4 and Google Search Console connectors for AI assistants. See the main repository for both endpoints and shared documentation.

Connect your Google Analytics 4 data to an AI assistant through a hosted, read-only MCP server.

MCP endpoint: https://ga4.vosiksignals.win/mcp

This repository documents the hosted service. The server's source code is not published here, and no self-hosted package is provided.

Features

  • Discover Google Analytics accounts and GA4 properties accessible to your Google account.
  • Query GA4 reports for selected date ranges.
  • Analyze traffic, users, acquisition, and other available metrics and dimensions.
  • Continue exploring results conversationally in an MCP-compatible AI client.

The server requests the Google OAuth scope https://www.googleapis.com/auth/analytics.readonly. Google has verified the OAuth application for this scope. Access is limited to the Google Analytics properties your Google account is permitted to view.

Connect

  1. In an AI client supporting remote MCP over Streamable HTTP and OAuth, add a custom MCP server.

  2. Use this URL:

    https://ga4.vosiksignals.win/mcp

  3. Follow the Google authorization flow.

  4. Ask the assistant to list your Google Analytics accounts and properties.

ChatGPT is the primary integration tested by the maintainer. Compatibility with other clients (including Claude and Cursor) depends on their remote MCP and OAuth support and has not yet been verified end-to-end.

Example prompts

  • List my Google Analytics accounts and properties.
  • Show sessions and active users for the last seven days, broken down by date.
  • Compare traffic for the last 28 days against the previous 28 days.
  • Show acquisition sources for a GA4 property.

Supported queries depend on the available MCP tools, the Google Analytics API, and your property permissions.

Security and privacy

  • Google OAuth authorization is required.
  • Google Analytics access is read-only.
  • OAuth credential properties are encrypted at rest using AES-GCM by the OAuth provider; network connections use HTTPS/TLS.
  • Credentials are used for authenticated API requests, not included in normal report responses.

See the Privacy Policy for details on data handling, retention, and deletion.

Never include OAuth tokens, private analytics reports, or personal information in public GitHub issues.

Feedback

Use GitHub Issues to report bugs, request features, or share client compatibility results. Include the client name, error message, and reproduction steps, but redact sensitive information.

Service

This is documentation for a hosted service, not an open-source release of the server code.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.