Skip to content

MCP server

Google Analytics MCP server

Google Analytics' official MCP server lets AI run GA4 reports, funnels and realtime reports and read property settings. Read-only.

At a glance

Maintained by
Google Analytics (googleanalytics GitHub org)
Tools exposed
7 listed below
Reviewed
September 24, 2026

Why it matters

What it does and why it matters

Google Analytics holds the traffic and conversion data for most business websites, but its interface is hard for many people. The official Google Analytics MCP server lets an assistant list accounts and properties, read property details and custom definitions, list Google Ads links and run standard, funnel and realtime reports.

"Which pages brought the most leads last month" becomes a question with an answer, not a report someone has to build.

It is read-only and cannot change GA4 configuration, which makes it one of the safer servers to start with. Access follows the Google account you connect. Always check that the assistant used the right date range and metrics before sharing numbers.

Use cases

Best business use cases

Traffic questions

Ask about visits, sources and pages.

Funnels

See where visitors drop off before converting.

Realtime

Check traffic during a launch or campaign.

Monthly reports

Draft monthly traffic summaries. See automated reporting.

Campaign results

Compare campaign performance.

Tools

Available tools

Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.

Read and write: Read-only: reports and property settings; cannot change GA4 configuration.

  • get_account_summaries

    List your Analytics accounts and properties.

  • get_property_details

    Get details for one property.

  • list_google_ads_links

    List Google Ads links for a property.

  • run_report

    Run a report with the Data API.

  • run_funnel_report

    Run a funnel report.

  • get_custom_dimensions_and_metrics

    List a property's custom dimensions and metrics.

  • run_realtime_report

    Run a realtime report.

Workflows

Example workflows

Monthly marketing summary

  1. 1

    Ask for last month's key numbers.

  2. 2

    The assistant runs reports.

  3. 3

    It compares with the month before.

  4. 4

    It explains big changes.

  5. 5

    Marketing edits and shares it.

Launch day check

  1. 1

    During a launch, ask for realtime traffic.

  2. 2

    The assistant runs a realtime report.

  3. 3

    It shows top pages and sources.

  4. 4

    It repeats every hour.

  5. 5

    The team adjusts promotion.

Prompts

Example prompts

  • “Which pages brought the most form submissions last month?”

  • “Show the checkout funnel for the last 30 days and where people drop off.”

  • “How many people are on the site right now, and from where?”

Setup

Installation and configuration

Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.

Claude Desktop: claude_desktop_config.json

{
    "mcpServers": {
        "analytics-mcp": {
            "command": "pipx",
            "args": [
                "run",
                "analytics-mcp"
            ],
            "env": {
                "GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON",
                "GOOGLE_PROJECT_ID": "YOUR_PROJECT_ID"
            }
        }
    }
}

Claude Code: terminal

claude mcp add analytics-mcp --scope user -e "GOOGLE_APPLICATION_CREDENTIALS=PATH_TO_CREDENTIALS_JSON" -e "GOOGLE_PROJECT_ID=YOUR_PROJECT_ID" -- pipx run analytics-mcp
  • Local server: PyPI: analytics-mcp (run with pipx run, stdio).
  • Needs: Google Application Default Credentials with scope https://www.googleapis.com/auth/analytics.readonly, plus a Google Cloud project with the Analytics Admin and Data APIs on..

Security

Security considerations

  • Read-only

    It cannot change GA4 configuration.

  • Account access

    Connect an account with access to the right properties only.

  • Check the numbers

    Confirm date ranges and metrics before sharing.

  • Privacy

    Keep reports at aggregate level.

Related servers

Servers that pair well with it

BigQuery

Google's remote BigQuery MCP server lets AI list datasets and tables and run SQL, with a read-only query tool and IAM controls.

Google Sheets

Google's own Sheets MCP server lets AI read and update cell values and formulas, change spreadsheet structure and insert rows or columns.

HubSpot

HubSpot's official hosted MCP server lets AI search and manage CRM records, query CRM data and work with marketing emails, pages and posts.

Keep exploring

FAQ

Questions people ask us

Have a question that is not here? Ask us directly.

Start a project

Want this connected to your own systems? We build AI workflows with MCP.

Send a short brief. We reply with questions, a suggested plan and an estimate you can compare with other offers.

Your privacy choices

We use necessary storage to run this site. With your permission we also use Google Analytics to see which pages help people, and load maps from Google. You can change this at any time. Read the cookie policy.