How to Query Google Analytics 4 with Claude / Cursor via MCP (Google Analytics MCP Server Setup)

See everything Query Streams can do beyond this guide Get Started Free

Supports

+more

Live Data

Replace exports with on-demand SQL

Excel Sheets

BI & AI Analytics

Ask Nova, get SQL + charts

Meet Nova

Database REST API

One key per partner. No credentials shared.

Build an API

+more

Automation

Scheduled sync to 6+ platforms

Explore

+more

API to SQL

Query APIs with SQL, no code

Explore

+more

AI Database MCP

Claude, Cursor, ChatGPT & Grok talk to your data

Connect AI

Query Streams is a secure, real-time data integration platform that brings every database and SaaS API in your account into Claude, Cursor, ChatGPT, and Grok — through a single MCP key with no firewall changes. This google analytics mcp guide walks through wiring up the Google Analytics 4 connector specifically, so your AI tool can answer plain-English questions about pageviews, sessions, traffic sources, and conversions without you exporting CSV reports out of the GA4 web UI. Learn more at QueryStreams.com and sign up for free to start asking your AI tool real marketing-analytics questions.

What the Query Streams Google Analytics MCP server gives you

Other “Google Analytics MCP” servers on the open-source landscape connect the AI tool straight to the GA4 Data API. That works, but it pushes a Google OAuth token into your AI client’s config, scopes the AI tool to only Analytics, and gives you no audit trail of what the AI actually asked. The Query Streams Google Analytics MCP server solves a wider problem: one key, every connector, full audit trail, and the AI tool never holds your Google credentials. The agent caches each GA4 property into a local DuckDB file so the LLM sees real SQL surfaces — tables, columns, joins, semantic types — instead of REST endpoints with opaque dimension and metric names.

How the Google Analytics MCP server works without opening firewall ports

The Query Streams Network Agent is a small program you install once on a machine that can reach the Google Analytics Data API (any laptop, server, or cloud VM). It opens one outbound TLS cloud link to the Query Streams cloud and waits there for tool calls. When Claude or Cursor asks a question, the cloud forwards the request to the agent, the agent calls the GA4 Data API, the agent caches the response in a local DuckDB so the AI can run SQL against it, and the result streams back through the same outbound channel. Nothing inbound. Nothing exposed. The AI tool never sees your Google OAuth token, and the GA4 MCP server never holds your credentials directly — the agent does, on your network.

The MCP key you give Cursor or Claude is scoped (read / analyze / execute), revocable at any time, and rate-limited per-key. The AI tool calls these MCP tools to do its work:

Why Schema Intelligence makes the GA4 MCP server different

Most “MCP for X” servers in the open-source landscape hand your AI tool the same information_schema your database hands a stranger. Column names. Data types. Maybe a primary key. For Google Analytics 4 specifically, the picture is even bleaker: a typical GA4 MCP server returns a flat list of GA4 dimension and metric names, the AI has to guess which metrics are summable vs. averaged, has no idea that engagement_rate is stored as a 0-1 decimal rather than a percentage, and has no clue that event_date is a YYYYMMDD-formatted integer rather than a real SQL DATE. That’s why the first SQL most LLMs write against a bare GA4 schema — whether returned by a generic GA4 MCP or by a generic ga4 mcp library — is wrong on the first try. It’s not that the LLM is bad. It’s that it doesn’t have the data it needs to be right.

The Query Streams MCP server returns that same schema enriched with what we call Schema Intelligence (SI) — AI-curated metadata generated by running profiling queries against your actual GA4 data before the AI client ever asks. When SI is enabled on a connector, every schema tool the AI calls (qs_get_connector_schema, qs_get_table_schema, qs_profile_table, qs_get_relationships) returns the bare schema plus six layers of curated knowledge. The LLM stops guessing on event names, traffic sources, device categories, custom dimensions, and that integer-encoded date column.

To make this concrete, here is what the AI client gets back from a single qs_get_table_schema call against the GA4 connector’s ga4_events table — first without Schema Intelligence, then with it.

The six layers Schema Intelligence adds

Each layer addresses a specific class of question the LLM would otherwise guess at, and SI runs as an opt-in, read-only profiling pass that never changes your schema. More on how Schema Intelligence is generated →

Same prompt, different SQL

The proof is in the SQL the AI tool actually writes. Same Cursor session, same Claude model, same prompt — “Show me my top 10 landing pages by engagement last month, where pageviews are over 100.” Without Schema Intelligence the LLM has to guess. With it, the LLM knows.

MCP not for you? Try Nova AI instead.

Skip MCP entirely: Nova AI is built right into the Query Streams web portal, so you can sign in and ask the same plain-English GA4 questions — “what’s our bounce rate trend over the last 90 days?” or “which content categories drive the most signups?” — with no config files and nothing to wire up.

Meet Nova AI

Prerequisites

Before you start, make sure you have:

1. A free Query Streams account at my.querystreams.com.
2. The Query Streams Network Agent installed on a machine with internet access — see Download the Query Streams Agent.
3. A Google Analytics 4 connector configured against the agent — see the existing API Connector Setup guides for OAuth pairing. The agent holds the Google OAuth token; the AI tool never touches it.
4. Any MCP-capable AI client. We’ll show Cursor, Claude Desktop, ChatGPT, and Grok in this guide; if you use Windsurf, Zed, Continue, Cline, VS Code Copilot, Codex, or Goose, the config block is essentially the same.
5. Five minutes.

Step 1: Generate a Google Analytics MCP key in Query Streams

Sign in to Query Streams and open the MCP page (or sign in first at my.querystreams.com and click MCP in the left navigation). The same Google Analytics MCP key reaches every connector in your account — not just GA4 — so you only ever generate one. Click Generate key, give the key a recognizable name (something like cursor-laptop or claude-desktop), and pick the scopes you want this key to have:

• read — the AI can browse connectors and read schema. Required for everything else.
• analyze — the AI can profile tables and discover relationships (sample values, distributions, semantic types). Optional but strongly recommended for analytics work, where understanding the shape of your event data matters.
• execute — the AI can actually run SQL. Without this, the AI is read-only against schema metadata only.

For a typical “let Claude analyse my Google Analytics data” workflow, all three scopes are appropriate. For a key you’re handing to a teammate or a less-trusted client, drop execute and let them browse only. You can revoke any key at any time from the same page; the AI client will see MCP_KEY_REVOKED on its next call and stop working immediately. There’s no propagation delay.

Copy the key now — Query Streams shows it once, then stores only a hash. If you lose it, generate a new one. The key looks like qsmcp_ followed by 48 random characters and is what your AI client sends in the X-MCP-Key request header.

Step 2: Add Query Streams MCP to your AI client

The configuration is the same shape across every MCP-capable client — an MCP server entry pointing at https://mcp.querystreams.com with your key in the X-MCP-Key header. Pick your client below.

Cursor ~/.cursor/mcp.json

// Edit ~/.cursor/mcp.json
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}

Claude Desktop claude_desktop_config.json

// Settings → Developer → Edit Config
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}

ChatGPT Apps & Connectors

// Settings → Apps & Connectors → Add MCP
Server URL  https://mcp.querystreams.com
Auth header X-MCP-Key
Header value qsmcp_PASTE_KEY_HERE

// Requires a paid ChatGPT plan
// (Plus / Pro / Team / Enterprise).

Grok Remote MCP Tools

// Grok → Settings → Tools
{
  "mcp_servers": [{
    "name": "querystreams",
    "url": "https://mcp.querystreams.com",
    "auth_header": "X-MCP-Key",
    "auth_value": "qsmcp_..."
  }]
}

Restart your AI client. On its next start it will discover the eight Query Streams MCP tools listed above and surface them in its tool palette. In Cursor and Claude Desktop you can verify by typing “list connectors” — the AI should call qs_list_connectors and return your Google Analytics 4 connector along with anything else you have configured.

Step 3: Ask the AI a Google Analytics 4 question

You don’t write SQL — the AI does. You ask a question, the AI picks the right MCP tool, the agent runs the query against your cached GA4 data, and the answer comes back as text plus tables. Three example prompts to try first:

The first time the AI calls a tool, your client may pop up a confirmation prompt asking you to approve the tool call — that’s MCP’s standard consent flow, not anything Query Streams adds. Approve once and the AI proceeds with the rest of the conversation freely. You can revisit the consent at any time in your client’s settings.

Frequently asked questions

Get started

Related guides: Download the Query Streams Agent | API Connector Setup | All MCP Server guides | Nova AI text-to-SQL

Category: MCP Server

Tags: mcp, claude, cursor, chatgpt, grok, google-analytics, ga4, web-analytics, marketing-analytics, api-connector, ai

Meta Description: Connect Claude or Cursor to Google Analytics 4 via MCP. Query GA4 data with AI in plain English. Free.