English Français العربية

Google Analytics 4

Registre officiel Marketing et ventes

Manage GA4 properties, data streams, conversions, and run reports via Admin & Data APIs.

Code source Documentation

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

PYPI package google-analytics-4-mcp
Claude Code 
claude mcp add google-analytics-4 -e 'GA_CREDENTIALS=<GA_CREDENTIALS>' -e 'GA_CREDENTIALS_PATH=~/.google-analytics-mcp/credentials.json' -- uvx google-analytics-4-mcp==0.1.1
Configuration JSON (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "google-analytics-4": {
            "command": "uvx",
            "args": [
                "google-analytics-4-mcp==0.1.1"
            ],
            "env": {
                "GA_CREDENTIALS": "<GA_CREDENTIALS>",
                "GA_CREDENTIALS_PATH": "~/.google-analytics-mcp/credentials.json"
            }
        }
    }
}

Variables d'environnement

  • GA_CREDENTIALS Google Service Account JSON key content (copy-paste the entire JSON)
  • GA_CREDENTIALS_PATH Alternative: path to the Service Account JSON key file

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. Google Analytics 4 MCP Server
  2. Setup (one-time, ~3 minutes)
  3. Installation
  4. Getting Started
  5. Tools (23)
  6. Environment Variables
  7. Example Usage
  8. License

Google Analytics 4 MCP Server

MCP server for Google Analytics 4 — create properties, configure data streams, manage conversions, and run reports via the Admin & Data APIs.

Setup (one-time, ~3 minutes)

  1. Google Cloud Console → IAM & Admin → Service Accounts
    • Create a service account (any name)
    • Click it → Keys → Add Key → JSON → Download
  2. Enable APIs in your GCP project:
  3. GA4 Admin → Property Access Management → Add the service account email (from the JSON) as Editor
  4. Configure credentials (pick one):
    • Option A (recommended): Copy the JSON content into the GA_CREDENTIALS env var in your MCP config
    • Option B: Save the file to ~/.google-analytics-4-mcp/credentials.json

Done. No browser flow, no consent screen, no tokens to refresh.

Installation

Claude Code
claude mcp add google-analytics -e GA_CREDENTIALS='{"type":"service_account",...}' -- uvx google-analytics-4-mcp
Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "google-analytics": {
      "command": "uvx",
      "args": ["google-analytics-4-mcp"],
      "env": {
        "GA_CREDENTIALS": "{\"type\":\"service_account\",\"project_id\":\"...\", ...}"
      }
    }
  }
}
From source
git clone https://github.com/stucchi/mcp-google-analytics.git
cd mcp-google-analytics
uv run google-analytics-4-mcp

Getting Started

  1. Check auth: Call check_auth_status to verify the service account is configured
  2. List accounts: Call list_accounts to see your GA4 accounts
  3. Setup a property: Use create_property → create_web_data_stream → get_tracking_snippet
  4. Query data: Use run_report with dimensions and metrics

Tools (23)

Auth
ToolDescription
check_auth_statusVerify service account is configured and valid
Admin API
ToolDescription
list_accountsList accessible GA4 accounts
list_propertiesList properties for an account
create_propertyCreate a GA4 property
get_propertyGet property details
delete_propertySoft-delete a property
list_data_streamsList data streams
create_web_data_streamCreate web stream → get Measurement ID
delete_data_streamDelete a data stream
get_tracking_snippetGenerate gtag.js HTML snippet
list_key_eventsList conversion events
create_key_eventMark event as conversion
delete_key_eventRemove conversion
list_custom_dimensionsList custom dimensions
create_custom_dimensionCreate custom dimension
list_custom_metricsList custom metrics
create_custom_metricCreate custom metric
list_google_ads_linksList Google Ads links
create_google_ads_linkLink Google Ads account
get_measurement_protocol_secretGet/create Measurement Protocol secret
Data API
ToolDescription
run_reportRun report with dimensions, metrics, dates, filters
run_realtime_reportReal-time active users and events
get_metadataList available dimensions and metrics

Environment Variables

VariableDefaultDescription
GA_CREDENTIALS—Service Account JSON key content (copy-paste the entire JSON)
GA_CREDENTIALS_PATH~/.google-analytics-4-mcp/credentials.jsonAlternative: path to the JSON key file

GA_CREDENTIALS takes priority over GA_CREDENTIALS_PATH.

Example Usage

You: "Set up Google Analytics for my website https://mcpadvisor.stucchi.consulting"

Assistant calls: list_accounts → create_property → create_web_data_stream → get_tracking_snippet

Result: Property created with Measurement ID G-XXXXXXXXXX and ready-to-paste HTML snippet.
You: "Show me the top 10 countries by sessions in the last 7 days"

Assistant calls: run_report(property_id="...", dimensions=["country"], metrics=["sessions"], start_date="7daysAgo", limit=10)

License

MIT

Questions fréquentes

Qu'est-ce que Google Analytics 4 ?

Manage GA4 properties, data streams, conversions, and run reports via Admin & Data APIs.

Comment installer Google Analytics 4 ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add google-analytics-4 -e 'GA_CREDENTIALS=<GA_CREDENTIALS>' -e 'GA_CREDENTIALS_PATH=~/.google-analytics-mcp/credentials.json' -- uvx google-analytics-4-mcp==0.1.1. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour Google Analytics 4 ?

Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.

Google Analytics 4 est-il open source ?

Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.

Qui maintient Google Analytics 4 ?

Il est publié par stucchi. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.