Free Google Analytics MCP: No-Code Setup

Q: What is the Google Analytics MCP server URL?

Porter's server URL is https://mcp.portermetrics.com/mcp, and you paste it into Claude, ChatGPT or any MCP client. Google's own server has no hosted URL. You install it from Google's analytics-mcp repository on GitHub and run it on your machine with Python and your own credentials.

Free forever plan: unlimited GA4 properties, no credit card.
Official Google Analytics API: one Google sign-in, no Python, no Cloud project, nothing to host.
Run GA4 end to end: reports, key events, property settings and live dashboards.
Safe by default: reading never changes your property; every change waits for your approval.

Try free

By Kashmala Malik · Last updated November 9, 2026 · All Google Analytics 4 destinations

What is a Google Analytics MCP server?

A Google Analytics MCP server lets an AI assistant like Claude or ChatGPT read your GA4 data through the Model Context Protocol (MCP). You ask in plain language, and the assistant calls Google’s Analytics Data and Admin APIs for sessions, landing pages, key events and property settings.

Quick setup: paste https://mcp.portermetrics.com/mcp into Claude, ChatGPT or Cursor and sign in with Google. Full steps
Works in: Claude, ChatGPT, Claude Code, Cursor, VS Code and Codex
Data: 288 GA4 fields plus your custom dimensions and metrics, realtime included, across every property your Google login can open
Changes: key events, custom definitions, audiences, data streams, Google Ads links and user access, each after your approval
Price: free plan, paid plans from $15 per property a month
Official Google server: yes, open source and read-only by default, run on your own machine with Python and a Google Cloud project

Use cases

Google Analytics MCP use cases

Ask why traffic moved, which pages convert and what to fix, and Claude answers from your live GA4 properties.

Reports

Channels and landing pages: Sessions, Engagement rate and Key events by Session default channel group and landing page.
Realtime: who is on the site right now, without opening GA4.
Live dashboards and weekly reports: one link, refreshed for every reader, or start from the free GA4 dashboard templates.
GA4 next to spend and the CRM: Sessions and Key events beside Meta Ads and Google Ads spend, or new contacts in HubSpot.
New vs returning: Sessions, Engagement rate and Key events for new and returning users, by channel.
Peak hours and events: traffic and Key events by hour and weekday, plus Event count per event, to see which actions people take and when.

Research

Traffic from AI assistants: Sessions from chatgpt.com, perplexity.ai and other AI sources by month.
Search Console next to GA4: Clicks and Average position from the Search Console MCP beside what visitors did after the click.
Every property you can open: compare client properties in one chat, ranked by Key events.
Back to the first day: paid plans query from the property’s first day, and Google’s note that data retention doesn’t affect standard reports means those totals stay complete.

Audits

Traffic drops: the day, device and channel where Sessions fell.
Key event checks: Event count by Page path shows where each key event fires, and which never fire.
Weak landing pages: pages with many Sessions but a low Engagement rate.
Property setup: data streams, custom definitions, Google Ads links and who has access, listed in one answer.

Management

Key events: mark an event that already fires as a key event, or change how it counts.
Custom dimensions and metrics: create one from an event parameter you already send.
Audiences: build a GA4 audience from a description of who belongs in it.
Streams, links and access: add a data stream, link a Google Ads account, or add a teammate with the right role.

Example answer

Demo data, from a fictional property. Prompt: “Show Sessions, Engagement rate, Key events and Purchase revenue by Session default channel group for last month, with the key event rate for each.”

Session default channel group	Sessions	Engagement rate	Key events	Key event rate	Purchase revenue
Organic Search	48,210	64.2%	1,930	4.0%	$58,410.00
Paid Search	21,870	58.7%	1,155	5.3%	$41,280.50
Email	9,420	70.1%	612	6.5%	$22,975.00
Organic Social	12,650	41.8%	188	1.5%	$4,120.00
Referral	3,980	55.3%	96	2.4%	$2,210.00

Organic Social brings plenty of sessions but converts at about a third of Organic Search’s rate, so Claude flags its landing pages for review.

Reference

Google Analytics MCP server reference

One MCP server: Porter connects Google Analytics 4 to the AI clients, fields, metrics, dimensions and workflows marketers already use. You paste one server URL and sign in with Google once. Every client you add then reads the same 288 fields, and the same server reaches the sources in all MCP connectors.

AI clients

Only one AI app?

ClaudeGoogle Analytics connector

ChatGPTGoogle Analytics connector

GA4 objects

Objects: properties · data streams · key events · custom dimensions · custom metrics · audiences · users

GA4 metrics

Traffic: Sessions · Total users · New users

Engagement: Engaged sessions · Engagement rate · Average session duration

Conversion: Key events · Event count · Purchase revenue · Ecommerce purchases

Definitions for each one are in the GA4 field definitions.

GA4 dimensions and segments

Acquisition: Session default channel group · Session source / medium

Content: Landing page + query string · Page path · Page title · Event name

Audience: Device category · Country

Time: Date · Week · Month and year

Rule of thumb: GA4 updates through the day, so prompts ask for periods ending two days ago.

GA4 actions

Read actions: properties and their settings (property_list, property_get, metadata_get) · reports and realtime (report_run, report_realtime) · key events, custom definitions, audiences, streams, Google Ads links and users (conversion_list, customdimension_list, custommetric_list, audience_list, datastream_list, googleadslink_list, user_list)

Write actions (each asks you first): mark or update key events (conversion_create, conversion_update) · create custom dimensions, metrics and audiences (customdimension_create, custommetric_create, audience_create) · add streams, Google Ads links and users (datastream_create, googleadslink_create, user_add, user_update)

Remove actions (permanent, each asks you first): conversion_delete · googleadslink_delete · user_delete · property_delete (GA4 keeps a deleted property in the trash for 35 days)

Not available: the GA4 tag on your site and BigQuery export links aren’t managed here.

Related MCPs

Pair GA4 with the Google Search Console MCP, the Google Ads MCP, the Meta Ads MCP or the HubSpot MCP. One Porter connection covers all of them, or see every MCP server.

Other destinations

The same Google Analytics connection also sends data to Data Studio (formerly Looker Studio), BigQuery and Google Sheets, at no extra cost.

Start from the free Google Analytics 4 dashboard templates.

Security and trust

Safety and security

Porter’s Google Analytics connection reads first and asks before any change. A Viewer role is enough to report, an Editor role lets Claude change settings, and every change waits for your approval. Actions GA4 can’t undo, like removing a key event, are flagged as permanent, so you confirm them before they run.

Read-only first

Read-only first: ask about sessions, pages and key events without changing anything in the property. Reporting runs apart from settings changes.

Unlimited reporting queries

Unlimited reporting queries: ask as many questions as you need. Porter works within Google’s Data API quota of 200,000 core tokens per property per day, so you never track tokens yourself.

Approved Google sign-in

Approved Google sign-in: connect with your Google account. You never create a Cloud project, a service account or a credentials file.

Viewer to read, Editor to change

Your role decides the scope: Google Analytics roles (Viewer and Editor) carry over. Viewer reads reports; Editor is needed for key events, custom definitions and streams.

Changes after you approve

Changes after you approve: Claude shows the key event, dimension or audience it will create. Nothing reaches GA4 until you say yes.

Permanent actions flagged

Permanent actions flagged: removing a key event, unlinking Google Ads, deleting a data stream or removing a user can’t be undone in GA4. Porter flags each one and asks you to confirm.

Official API, no browser automation

Official API: Porter uses Google’s Analytics Data and Admin APIs, never a browser session clicking through GA4.

Revoke access anytime

Revoke access: disconnect Google Analytics from your Porter account whenever you want. Access stays tied to that sign-in, not a key on your laptop.

Setup

How to set up the Google Analytics MCP server

Paste this server URL into your AI app, then sign in with Google:

https://mcp.portermetrics.com/mcp

First, create a free Porter account and connect Google Analytics: Create → pick your AI app as the destination → Google Analytics 4 → sign in with Google → select your properties.

Before you connect: Viewer access to a property is enough for reports. Key events and audiences need Marketer or Editor, other settings need Editor, and user access needs Administrator, per Google’s GA4 roles guide.

How to install Google Analytics MCP in Claude

Open claude.ai and go to Settings → Connectors.
Click Add custom connector.
Name it Porter and paste https://mcp.portermetrics.com/mcp.
Click Add, then sign in with the Google account you use in Porter and approve access.
Ask Claude your first GA4 question.

On Team and Enterprise plans, an owner adds the connector first. Anthropic’s custom connector guide covers the same steps.

Watch the Claude setup demo

How to install Google Analytics MCP in ChatGPT

ChatGPT has two routes to the same data. The Porter Metrics app in ChatGPT’s app directory works on any plan with apps. The Porter MCP gets every new tool the day Porter ships it, on Business, Enterprise and Edu workspaces.

Porter Metrics app: in ChatGPT, open Apps, search “Porter Metrics”, click Connect and sign in with the Google account you use in Porter.

Porter MCP:

Open ChatGPT on the web and go to Plugins.
Click +, then Add custom MCP server.
Name it Porter and paste https://mcp.portermetrics.com/mcp under Connection.
Choose OAuth, tick “I understand and want to continue” and click Create as a plugin.
Sign in with the Google account you use in Porter.

Pro accounts can add it with read access only, per OpenAI’s custom MCP server guide.

Watch the ChatGPT app demo

How to install Google Analytics MCP in Claude Code, Cursor, VS Code and Codex

Pick your coding agent. Each one uses the same server URL and a Google sign-in, so no API key or credentials file sits in a config.

Add Porter’s plugin in Claude Code. It installs the Porter connector and Porter’s skill in one step.
/plugin marketplace add portermetrics/porter /plugin install porter-metrics@portermetrics
Ask for your data. The first time, your browser opens: sign in with the Google account you use in Porter.
No plugins? Add the server directly instead:
claude mcp add --transport http porter https://mcp.portermetrics.com/mcp
Check: /mcp shows porter as connected. Ask: “Which Google Analytics accounts can you see?”

Open Cursor Settings → Tools & Integrations and click New MCP Server. Cursor opens mcp.json.
Paste this and save.
{ "mcpServers": { "porter": { "url": "https://mcp.portermetrics.com/mcp" } } }
Click Connect next to porter and sign in with the Google account you use in Porter.
Check: porter shows a green dot in Tools & Integrations. Open an Agent chat. Ask: “Which Google Analytics accounts can you see?”

Open the Command Palette (Ctrl/Cmd+Shift+P) and run MCP: Add Server → HTTP.
Paste https://mcp.portermetrics.com/mcp, name it porter and choose Global. Or add it to .vscode/mcp.json:
{ "servers": { "porter": { "type": "http", "url": "https://mcp.portermetrics.com/mcp" } } }
Allow the sign-in prompt and sign in with the Google account you use in Porter.
Check: open Copilot Chat in Agent mode; Porter’s tools appear under the tools icon. Ask: “Which Google Analytics accounts can you see?”

Add Porter from your terminal.
codex mcp add porter --url https://mcp.portermetrics.com/mcp
Sign in. Your browser opens: sign in with the Google account you use in Porter.
codex mcp login porter
Check: codex mcp list shows porter as logged in. Start codex. Ask: “Which Google Analytics accounts can you see?”

The same URL works in Windsurf, Cline, Zed and any client that supports remote MCP servers over HTTP.

Add Porter’s skill

Porter’s skill teaches Claude which Porter tools to call for each GA4 task, so answers need fewer retries. In claude.ai, download https://mcp.portermetrics.com/skill.zip and upload it in Settings → Capabilities → Skills. In Claude Code, Porter’s plugin adds it for you, and other agents can run npx skills add portermetrics/porter.

Test the connection

Paste this into a new chat. It only reads data.

Use Porter only. List my GA4 properties. For the first one, show Sessions, Engagement rate and Key events by Session default channel group for the 7 days ending two days ago. Say so if a property returns no data.

Guides and videos

VideoConnect Google Analytics 4 to ClaudePorter Metrics on YouTube

→

TutorialHow to connect Google Analytics 4 to Claude

→

TutorialHow to connect Google Analytics 4 to ChatGPT

Prompts

Google Analytics MCP prompts

Copy a prompt into Claude or ChatGPT, then change the dates to fit your property. Reporting and research prompts only read the property; management prompts wait for your approval.

Reporting prompts

Channel report

For the last 28 days ending two days ago, show Sessions, Engaged sessions, Engagement rate and Key events by Session default channel group.

Landing page engagement

Show the 20 landing pages with the most Sessions in the last 28 days, with Engagement rate and Key events. Flag pages with high Sessions and low Engagement rate.

Traffic drop diagnosis

Sessions dropped last week. Compare Sessions and Key events by Date, Device category and Session default channel group with the week before, and find where the drop started.

Client property comparison

Compare Sessions, Engagement rate and Key events for the last 28 days across every GA4 property I’ve connected, ranked by Key events.

Weekly report

Write a weekly GA4 report: what changed in Sessions and Key events, which channels and landing pages moved it, and what to check next.

Research and audit prompts

Search Console vs GA4 engagement

For my top 20 landing pages in the last 28 days, show Search Console Clicks and Average position. Next to them, show GA4 Sessions, Engagement rate and Key events.

AI assistant traffic

Show Sessions, Engagement rate and Key events by Session source and Month and year for the last 6 months. Keep sources like chatgpt.com, perplexity.ai and claude.ai.

Key event audit

List the key events on this property. Then show Event count by Event name and Page path for the last 28 days, and flag key events that never fired.

Management prompts

Mark a key event

The event generate_lead fires but isn’t a key event. Mark it as a key event on my GA4 property after I approve.

Add a custom dimension

Create an event-scoped custom dimension called Plan type from the parameter plan_type. Show me the settings and create it only after I approve.

Tracking alert agent

Every Monday, compare Key events by Event name with the week before. Alert me when any key event drops by more than half.

Weekly summary

Every Monday, write a 10-line GA4 summary of Sessions, Key events and the top movers, ready to paste into our team channel.

Who this is for

Marketers who need the why behind the traffic. Porter’s Google Analytics connection fits four groups. Agencies report on many client properties, and in-house marketers own the website numbers. SEO and content marketers track organic and AI traffic, and analysts keep tracking clean. Each group below gets four jobs it can hand over.

Agencies and freelancers

Every client property: one answer across all of them, without switching GA4 views.
Client reports: a live link the client opens on Monday that you never rebuilt.

In-house marketers

Channel answers: which channel moved Key events this month, without building an exploration.
Landing pages: pages with traffic but no engagement surface on their own.

SEO and content marketers

Search Console next to GA4: clicks and position beside what visitors did after landing.
AI assistant traffic: sessions from ChatGPT, Perplexity and Claude, tracked by month.

When to use Google’s own instead

You’re a developer, read-only access is enough, and you’re happy to run Python with a Cloud project. Google’s server is free, open source and enough for that job.

Comparison

Official Google Analytics MCP vs. Porter

Google publishes an open-source Google Analytics MCP server that runs on your own machine. Google’s Analytics MCP setup guide describes it as read-only and lists its requirements (as of November 2026). It suits developers, and it can run next to Porter in the same AI client.

Google’s server gives your AI read access to GA4 from your laptop. Porter gives it your marketing operation: GA4, Search Console, ad spend, dashboards and approved fixes from one hosted URL.

The basics are the same on both: Google’s official Analytics APIs, your existing GA4 access, every report field GA4 exposes, and a server any MCP client can use. Here is where they part.

	Porter	Google’s official MCP (as of November 2026)
Same job, different reach
Steps before your first question	3: connect GA4 in Porter, paste the URL, sign in with Google	Python 3.10+ and pipx, a Cloud project with the Admin and Data APIs, Application Default Credentials, then a local config
Credential files on your computer	None	Application Default Credentials (or a service-account key)
Tools	Read, write and remove actions for reports, key events, custom definitions, audiences, streams, links and users	9 read tools, such as `run_report` and `run_realtime_report`, plus `create_property_annotation` with --allow-write
Where it runs	Hosted by Porter	On your machine, through pipx
Changes to GA4	Key events, custom dimensions and metrics, audiences, streams, Google Ads links, user access	Property annotations only, behind an --allow-write flag
Approval controls	Every change shown first and approved	Read-only by default
Clients in its docs	Claude, ChatGPT, Gemini, n8n, any remote MCP client	Antigravity, Claude Desktop, Claude Code
Price	Included in every Porter plan, the free plan too	Open source
Only one side
Search Console and other channels	30+ sources: Search Console, Google Ads, Meta Ads, HubSpot and more	GA4 only
Cross-channel in one conversation	Yes	Not in its docs
Blending sources into one number	Yes	Not in its docs
Live dashboards at their own link	Yes	Not in its docs
Scheduled reports and alerts	Yes	Not in its docs
Attribution to CRM revenue	Yes	Not in its docs
Data Studio, Sheets, BigQuery	Yes	MCP clients only
Skills: whole tasks already written	Yes	You write the prompt

Use Google’s own if you’re a developer, need GA4 only, and read-only access is enough. Everything under Only one side is what happens when the job grows past that.

Porter vs other hosted Google Analytics MCPs

Hosted GA4 MCPs such as ga4mcp.com and InsightfulPipe also skip the Python and Cloud setup. Porter is built for teams that report on several properties and channels:

Every property at once

One prompt answers for all your client properties, not one property per setup.

GA4 next to 30+ sources

Search Console, Google Tag Manager, Google Ads, Meta Ads and HubSpot, blended in one answer.

Competitor SEO data

Keywords, live search results and competitor pages, next to your own GA4 numbers.

Reports outside the chat

Live dashboards, scheduled email reports, and the same data in Data Studio, BigQuery and Google Sheets.

Tracking fixes with approval

Key events, custom definitions and audiences, each change shown first.

Claude and ChatGPT both covered

A remote MCP URL, plus an approved app in ChatGPT’s app directory.

Google Analytics MCP pricing

The Google Analytics MCP is included in every Porter plan, the free-forever plan too. Reporting is billed per connected account, and each GA4 property counts as one account.

14-day trial: everything unlimited, no credit card.
Free forever: unlimited connected accounts, 30 days of history (15 days in AI chats), 100 automation credits a month.
Paid Reporting: from $15 per account a month, or $12.50 billed annually.
Unlimited questions: AI chats, queries and dashboards are included. Reads are free; each completed change uses 1 automation credit.

How many accounts will you connect?

5 accounts

Monthly billing

$40

Annual billing, per month

$33.33

Per account

$8.00

Reporting price for connected accounts, in USD. AI chats, queries and dashboards are unlimited. Annual billing is 10 months for 12.

The more accounts you connect, the lower the price per account. See the full calculator on Porter pricing.

Frequently asked questions

Is there an MCP for Google Analytics?

Yes. Google publishes an open-source server you run locally, and Porter hosts one at https://mcp.portermetrics.com/mcp. Both read GA4 through Google's official APIs. Porter adds a Google sign-in instead of a Cloud project, Search Console and ad data in the same chat, and key event fixes after approval.

Does Google have an official Google Analytics MCP?

Yes. Google's Google Analytics MCP server is open source and runs locally with Python 3.10 or higher, a Cloud project and Application Default Credentials. Google describes it as read-only. Its only write tool, property annotations, needs an --allow-write flag (as of November 2026).

Is there a Google Analytics MCP on GitHub?

Yes. Google's own server lives in the googleanalytics/google-analytics-mcp repository, and community servers exist too. Each one runs on your machine with your own Google Cloud project and credentials. Porter's is hosted, so there's nothing to install.

What is the Google Analytics MCP server URL?

Porter's server URL is https://mcp.portermetrics.com/mcp, and you paste it into Claude, ChatGPT or any MCP client. Google's own server has no hosted URL. You install it from Google's analytics-mcp repository on GitHub and run it on your machine with Python and your own credentials.

Is GA4 MCP the same as Google Analytics MCP?

Yes. Google Analytics 4, or GA4, is the current version of Google Analytics, so both searches point to the same kind of server. Porter's Google Analytics connection reads GA4 properties, and its fields use the names you see in GA4, like Sessions and Key events.

Is the Google Analytics API free?

Porter's MCP costs nothing on any Porter plan, and it reaches GA4 through Google's official APIs within Google's property quotas. What you pay Porter for is Reporting, per connected property, and Automation credits when Claude changes settings. The free plan covers 30 days of history and 100 credits a month.

Why don't the numbers match the GA4 interface?

Check the date range, the property's time zone and whether the last two days are still processing. GA4 can also hide small rows for privacy (data thresholds), so totals by age or gender can come out lower.

Why does a change fail with a permission error?

Your Google login needs Marketer or Editor on the property to change key events and settings, and Administrator to manage users. Viewer access can report but not edit.

Why don't I see one of my properties?

Porter lists the properties your Google login can open. Ask the property's Administrator to add you, then reconnect GA4 in Porter.

Why does a query return no rows?

Check the property, the date range and the field names. Some dimensions and metrics can't be combined in one GA4 report, and an empty result isn't a permission error.

Start free

Connect Google Analytics to Claude or ChatGPT and ask why traffic moved, which pages convert and what to fix today.

Start free: unlimited GA4 properties, no credit card.

Start free with Google Analytics

For agencies: every client property answers in one chat, and the Monday report is a link.
For SEO and content marketers: Search Console and GA4 finally sit in the same answer.
For analysts: broken key events reach you as a fix to approve, not a surprise in the report.