Connect Google Analytics to Claude Code

Let Claude query reports and configure your property in Google Analytics. From the terminal, inside the sessions where you already work.

Build my connector Talk to us

How do you connect Google Analytics to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Google Analytics, you add a Google Analytics MCP server: a small hosted service that exposes Google Analytics's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Google Analytics account. No API keys pasted into config files.

claude mcp add --transport http google-analytics https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Google Analytics once connected?

Full read-write access lets Claude query report data and also manage the property: create or edit conversion events and audiences, set up custom dimensions and metrics, add event-create rules on a data stream, and manage links to other Google products, each behind your approval. The setup work that used to mean clicking through the Admin panel happens in context.

Mark a key event as a conversion in a GA4 property
Create an audience from a behavior or traffic segment you describe
Define a custom dimension or metric for event reporting
Create an event-create rule on a data stream
Create a property link to a connected Google product after you confirm

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Google Analytics access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Google Analytics API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Google Analytics changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Google Analytics connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Google Analytics connector work in claude.ai and Claude Code?

Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Google Analytics account, so access always matches what that person can already see and do.

Do I need to host or maintain anything myself?

No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Google Analytics's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.

Is it safe to give a coding agent write access to Google Analytics?

Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Google Analytics account it signs in with. Revoking access is one click in Google Analytics.

More on the Google Analytics connector

Google Analytics connector for claude.ai Mixpanel + Claude Code Mailchimp + Claude Code Google Sheets + Claude Code

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.

Build my connector Talk to us