[Connect AI to your data](/about/connect-ai-to-marketing-data) November 13, 2026 # Connect GA4 to Claude with Google’s MCP server Set up Google’s Analytics MCP server in Claude Desktop, Claude Code or claude.ai, see what it reads and changes, and the no-code fallback through Sheets. ![](/images/65d75b0ae8d69ef95785a5d6_david-pombar.webp) **[David Pombar](/authors-guides/david-pombar)** Swiss army knife at Trackingplan 7 min read · 1491 words > **TL;DR** To connect GA4 to Claude, use Google’s own Google Analytics MCP server. In Claude Desktop and Claude Code it runs on your computer: one config entry or one command. For claude.ai on the web or your phone, you host the same server over HTTPS and add its URL as a custom connector. It’s read-only unless whoever starts it adds `--allow-write`. No time for setup? Export the report to Google Sheets and let the Drive connector read it. Search for this and you’ll find two kinds of answers: connector services that hold a Google token on your behalf, and threads asking why there’s no Google Analytics button in Claude. The short version: Google wrote the server, Anthropic didn’t write a connector, and the Claude app you use decides how much work the setup is. This guide is part of a series on [connecting AI assistants to marketing data](/guides/connect-ai-to-marketing-data). It covers the official route in each Claude app, what the server can read and change, and the fallback when you can’t install anything. ![Two white plug adapters on a wooden desk, a small two-pin one and a larger square one](/images/connect-ga4-to-claude-adapters.jpg) Same socket, different adapter: the server stays the same, the Claude app decides how you plug it in. Image: Fructibus, Wikimedia Commons, CC0 ## Pick the route by Claude app ![Diagram of four ways to connect GA4 to Claude: Google’s MCP server on your computer for Claude Desktop, the same server added with one command in Claude Code, the server hosted over HTTPS as a custom connector for claude.ai on web and mobile, and a report exported to Google Sheets and read through the Drive connector.](/images/connect-ga4-to-claude-routes.webp) The server is the same in the first three routes; only where it runs changes. | Claude app | Route | What you need | | --- | --- | --- | | Claude Desktop | Google’s server, running locally | Python, a Google Cloud project, Viewer on the property | | Claude Code | The same server, added with `claude mcp add` | The same | | claude.ai (web and mobile) | The same server, hosted, added as a custom connector | A public HTTPS URL and an OAuth client | | Any | A report exported to Google Sheets | The Drive connector | Why the split: [Anthropic’s help center](https://support.claude.com/en/articles/11176164-connectors-in-claude) says custom connectors connect from Anthropic’s cloud, not from your device. A server on your laptop works in the desktop app and in Claude Code, never in the browser. ## Before any route: the Google side [Google’s developer docs](https://developers.google.com/analytics/devguides/MCP) list four prerequisites: 1. Python 3.10 or higher, and `pipx` or `uv` to run the server. 2. A Google Cloud project with the **Google Analytics Admin API** and the ** Google Analytics Data API** enabled. 3. At least the **Viewer** role on the GA4 property, for your user or for a service account. 4. Application Default Credentials with the scope `https://www.googleapis.com/auth/analytics.readonly`. With your own user, that’s `gcloud auth application-default login` with that scope. Copy the path of the credentials file it prints. Viewer is enough to read. The server sees the properties that account can see, and nothing else. ## Claude Desktop: the server on your computer Google documents this route directly. Add the server to `claude_desktop_config.json`, which lives in `~/Library/Application Support/Claude/` on macOS and `%APPDATA%\Claude\` on Windows: ```json { "mcpServers": { "analytics-mcp": { "command": "pipx", "args": ["run", "analytics-mcp"], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON", "GOOGLE_CLOUD_PROJECT": "YOUR_PROJECT_ID" } } } } ``` Replace the two values with the credentials path and your project ID. To check it loaded, ask Claude “what can the analytics-mcp server do?”, the first test prompt in Google’s README. ## Claude Code: one command In a terminal, from [Google’s repository](https://github.com/googleanalytics/google-analytics-mcp): ```bash claude mcp add analytics-mcp \ --scope user \ -e "GOOGLE_APPLICATION_CREDENTIALS=PATH_TO_CREDENTIALS_JSON" \ -e "GOOGLE_CLOUD_PROJECT=YOUR_PROJECT_ID" \ -- pipx run analytics-mcp ``` `--scope user` makes it available in every project on your machine. Claude Code is the better fit when the GA4 answer feeds something else: a SQL query, a dashboard file, a tracking fix in the same repository. ## claude.ai on the web: host it, then add a custom connector This is the route with the most work, and the only one that reaches the browser and the mobile app. **Host the server.** Google’s README documents an HTTP mode with a built-in OAuth 2.1 server, so each person signs in with their own Google account. You start it with `--transport http --oauth`, a Google OAuth web client ID and secret, and an issuer URL. The README walks through a Cloud Run deploy. One limit to plan for: the built-in OAuth provider keeps registrations and refresh tokens in memory, so you run a single instance, and a restart means everyone signs in again. **Add it to Claude.** On Free, Pro, Max or Ultra, per [Anthropic’s connector docs](https://claude.com/docs/connectors/custom/add-unlisted.md): 1. Go to **Customize > Connectors**, then ** Add > Add custom connector**. 2. Enter a name and the server URL, then select **Continue**. 3. Choose the authentication settings. 4. Select **Add**, then ** Connect**, and sign in with Google. Free accounts can add one custom connector. On Team, only Owners and Primary Owners add one, from **Organization settings > Connectors**; members then connect with their own login. In a chat, turn it on from ** \+ > Connectors**. ## Read-only, until someone turns writes on Google’s docs page and its GitHub README seem to disagree. Both are right; they describe different starts. - Google’s setup page says the server “is available for read requests only”. That describes the server as you install it. - The [README](https://github.com/googleanalytics/google-analytics-mcp) lists three write tools: `create_property_annotation`, `create_custom_dimension` and `create_key_event`. Each needs the `--allow-write` flag and the `analytics.edit` scope. Custom dimensions also need the Editor role; key events need Marketer or Editor. - Without the flag, `ANALYTICS_MCP_ALLOW_WRITE` defaults to `false`, and no write tools are offered. So: read-only by default, three narrow writes by choice. None of the tools deletes anything. On the Claude side, each connector has **Tool permissions**: set write tools to ** Needs approval** or ** Blocked**. Do it before you use Research, which can call connector tools without asking. ## No setup: Sheets and the Drive connector When you can’t install Python or create a Cloud project, take the report to Claude instead: 1. In GA4, open the report from **Reports** (not in Customize report mode). 2. Select **Share this report > Download File > Export to Google Sheets**. Google’s [export help](https://support.google.com/analytics/answer/9317657) caps it at 100,000 rows. 3. In Claude, connect the Google Drive connector, which Google builds and runs, and ask about the sheet. It’s a snapshot: no new dates, no new dimensions without another export. If your team already exports GA4 to BigQuery, query the raw events instead; our guide to [connecting BigQuery to Claude](/guides/connect-bigquery-to-claude) covers that, and the [GA4 BigQuery export schema](/guides/ga4-bigquery-export-schema) explains the tables. ## What to ask once it’s connected Each prompt maps to a tool the server exposes: | Ask | Tool it uses | | --- | --- | | Which landing pages lost the most sessions from Organic Search in the last 28 days? | `run_report` | | Where do users drop between `view_item`, `add_to_cart` and `purchase` this month? | `run_funnel_report` | | What’s ROAS by campaign for the last 30 days, under data-driven attribution? | `run_conversions_report` | | How many users are on the site right now, by country? | `run_realtime_report` | | Which custom dimensions exist, and which key events are defined? | `get_custom_dimensions_and_metrics`, `list_key_events` | | Is this property linked to a Google Ads account? | `list_google_ads_links` | Ask Claude to name the dimensions, metrics and date range it used. GA4 has several ways to count the same thing, and the answer changes with them. ## Before you trust the answers Claude gets what the Data API returns, which is what GA4 recorded. It doesn’t get how the hit was collected. If `purchase` stopped firing on Safari after a release, fires twice on the thank-you page, or arrives without its consent state, `run_report` hands Claude the damaged total, and Claude explains it as fluently as a correct one. Trackingplan watches the hits, the dataLayer and the consent signals your site sends to GA4 on real traffic, and catches missing properties, duplicate fires and consent breaches as they appear. An AI agent can only reason about what it can see. Its agent also works inside Claude, as the Ask Trackingplan tool, through the plan’s [MCP endpoint](/docs/mcp-endpoint): one connector for the numbers, one for whether to believe them. ## FAQ ### Is there an official Google Analytics connector for Claude? Google publishes an official Google Analytics MCP server and documents it for Claude Desktop and Claude Code. Anthropic’s docs don’t list a Google-built Google Analytics connector in the directory, so for claude.ai on the web you host Google’s server yourself and add its URL as a custom connector. ### Can Claude change my GA4 settings through the MCP server? Not by default. Google’s server starts read-only. Three write tools, for annotations, custom dimensions and key events, appear only if the server is started with `--allow-write` and the credentials carry the `analytics.edit` scope, plus the right role on the property. ### Does connecting GA4 to Claude work on the Free plan? Claude Desktop and Claude Code run the server on your computer. For claude.ai, custom connectors work on every plan, and Free accounts are limited to one. On Team plans only Owners can add a custom connector. ### How do I see visits from Claude in GA4? That is a different job: check **Session source / medium** in the Traffic acquisition report and add `claude.ai` to a custom AI channel, because GA4’s AI Assistant channel may not include it. Our guide to [tracking ChatGPT and AI traffic in GA4](/guides/track-chatgpt-ai-traffic-ga4) has the steps. Part of[Connect Claude or ChatGPT to your marketing data](/guides/connect-ai-to-marketing-data) On this page 1. [*01*Pick the route by Claude app](#pick-the-route-by-claude-app) 2. [*02*Before any route: the Google side](#before-any-route-the-google-side) 3. [*03*Claude Desktop: the server on your computer](#claude-desktop-the-server-on-your-computer) 4. [*04*Claude Code: one command](#claude-code-one-command) 5. [*05*claude.ai on the web: host it, then add a custom connector](#claude-ai-on-the-web-host-it-then-add-a-custom-connector) 6. [*06*Read-only, until someone turns writes on](#read-only-until-someone-turns-writes-on) 7. [*07*No setup: Sheets and the Drive connector](#no-setup-sheets-and-the-drive-connector) 8. [*08*What to ask once it’s connected](#what-to-ask-once-it-s-connected) 9. [*09*Before you trust the answers](#before-you-trust-the-answers) 10. [*10*FAQ](#faq) **Stop babysitting tags** Trackingplan audits your real user data around the clock and flags issues before they cost you. [Start free trial →](https://app.trackingplan.com/signup) ![](/images/65d75b0ae8d69ef95785a5d6_david-pombar.webp) **David Pombar** Swiss army knife at Trackingplan Read more from David, a Senior Product Strategist with 18+ years in digital product development and an atypical error detection knack. Share Copy link [LinkedIn](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fwww.trackingplan.com%2Fguides%2Fconnect-ga4-to-claude) [X](https://twitter.com/intent/tweet?url=https%3A%2F%2Fwww.trackingplan.com%2Fguides%2Fconnect-ga4-to-claude&text=Connect%20GA4%20to%20Claude%20with%20Google%E2%80%99s%20MCP%20server) Read next [All Guides →](/guides) - [ 7 minConnect AI to your dataNovember 13, 2026 ### How to connect GA4 to ChatGPT: three routes Add Google’s Analytics MCP server to ChatGPT as a custom MCP server, query the GA4 BigQuery export, or upload a report, with the plan each route needs. by **David Pombar**](/guides/connect-ga4-to-chatgpt) - [ 7 minConnect AI to your dataNovember 13, 2026 ### Connect BigQuery to Claude: connector, roles and cost caps Add Google’s BigQuery connector to Claude or run MCP Toolbox on your machine, with read-only roles and a cap on what each query can scan. by **David Pombar**](/guides/connect-bigquery-to-claude) - [ 7 minConnect AI to your dataNovember 13, 2026 ### Connect Google Analytics to Gemini or Copilot Gemini and Copilot have no Google Analytics connector, so use Ask Advisor inside GA, Google’s Analytics MCP server or an MCP tool in Copilot Studio. by **David Pombar**](/guides/connect-google-analytics-to-gemini-copilot) Trackingplan ## See everything. Miss nothing. Your implementations audited around the clock with real-time, real-user data. Real-time alerts about errors or changes in your data, campaigns, pixels, privacy and consent. Let AI flag issues before they cost you. [Start free trial →](https://app.trackingplan.com/signup) [Book a demo](/demo)