Google Analytics 4

Registre officiel Marketing et ventes

Google Analytics 4 MCP server: 27 read tools, no write tools.

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 »).

NPM package @getmcpads/google-analytics-mcp-server
Claude Code
claude mcp add google-analytics-4 -e 'GA4_CLIENT_ID=<GA4_CLIENT_ID>' -e 'GA4_CLIENT_SECRET=<your ga4_client_secret>' -e 'GA4_REFRESH_TOKEN=<your ga4_refresh_token>' -e 'GA4_PROPERTY_ID=<GA4_PROPERTY_ID>' -e 'GA4_PROPERTY_IDS=<GA4_PROPERTY_IDS>' -- npx -y @getmcpads/google-analytics-mcp-server@2.1.1
Configuration JSON (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "google-analytics-4": {
            "command": "npx",
            "args": [
                "-y",
                "@getmcpads/google-analytics-mcp-server@2.1.1"
            ],
            "env": {
                "GA4_CLIENT_ID": "<GA4_CLIENT_ID>",
                "GA4_CLIENT_SECRET": "<your ga4_client_secret>",
                "GA4_REFRESH_TOKEN": "<your ga4_refresh_token>",
                "GA4_PROPERTY_ID": "<GA4_PROPERTY_ID>",
                "GA4_PROPERTY_IDS": "<GA4_PROPERTY_IDS>"
            }
        }
    }
}

Variables d'environnement

  • GA4_CLIENT_ID obligatoire OAuth client ID.
  • GA4_CLIENT_SECRET obligatoire secret OAuth client secret.
  • GA4_REFRESH_TOKEN obligatoire secret OAuth refresh token, analytics.readonly scope.
  • GA4_PROPERTY_ID Default GA4 property ID.
  • GA4_PROPERTY_IDS Comma-separated property IDs every tool is limited to. Optional in 2.x, required in 3.0.0.

Documentation

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

Sommaire
  1. Google Analytics 4 MCP server
  2. What's new
  3. Install this release
  4. What you get
  5. Read-only, and why it stays that way
  6. Personal data
  7. Getting credentials
  8. Setup
  9. Tools
  10. Security
  11. Looking for a managed, multi-platform version?
  12. Contributing
  13. Licence
  14. MCP contracts and desktop bundle
  15. More from getmcpads

Google Analytics 4 MCP server

Understand what happens after the click.

Explore traffic, conversions, funnels and property configuration through a read-only MCP server.

Watch the film · What's new · Install · Tool reference · Try hosted getmcpads

Play the 45-second film

The film shows hosted getmcpads with sample data. Its MCP Apps, from creative galleries and alerts to Google Sheets exports and bulk launches, belong to the hosted product. This repository provides the standalone native API tools.

27 read tools · Read-only by design.

Run locally with your own platform credentials and a client that supports stdio MCP, such as Claude Desktop, Claude Code or Cursor. Your requests go directly to the platform. For managed connections, including supported ChatGPT setups, use the hosted option.

What's new

v2.1.0: Property allowlist and revoked-token handling · October 23, 2026

  • Add the optional GA4_PROPERTY_IDS allowlist, checked before every request. ga4_list_properties, ga4_list_accounts and ga4_health_check list only the allowed properties and the accounts that hold them. Unset, the server prints a recommendation on stderr. It becomes required in 3.0.0.
  • Refuse a GA4_PROPERTY_ID outside GA4_PROPERTY_IDS at startup, when both are set.
  • Port the gateway's handling of a refused refresh token (invalid_grant, admin_policy_enforced): one re-authorization message naming GA4_REFRESH_TOKEN, and no further token requests until restart.
  • Give the token request a deadline and bound every response body.
  • Require Node.js ^22.23.4 || ^24.22.1 || >=26.12.1, warn on stderr at startup and in npm run doctor on older releases, and test Node 22, 24 and 26 in CI.
  • Update @modelcontextprotocol/sdk to 1.32.1 and regenerate the lockfile.
  • Publish from version tags with release.yml, which replaces publish-mcp.yml. Add Dependabot.
  • No tool is added or removed: 27 read tools, no write tools.

Earlier releases

VersionDateHighlights
2.0.1September 23, 2026Public repository restored
2.0.0September 20, 2026Gateway sync and security fixes
1.1.0September 13, 2026Platform capability sync and quality contracts
1.0.2August 30, 2026Announce the package version over MCP.
1.0.1August 30, 2026Add server.json and mcpName for the official MCP Registry, under com.getmcpads/google-analytics.
1.0.0August 29, 2026First open-source release

Full changelog · All releases

Source synchronization: SOURCE_SYNC.md.

Upgrade notes

Requires Node.js 22.23.4, 24.22.1 or 26.12.1, or a newer release of one of these lines. Older releases lack the October 2026 security fixes, and the server prints a warning on stderr when it starts on one. CI covers Node 22, 24 and 26.

This release makes no breaking change to the configuration. One change is announced for 3.0.0: GA4_PROPERTY_IDS is optional in 2.x and becomes required. When set, every tool is limited to the listed properties, and GA4_PROPERTY_ID must be one of them. When unset, the server starts as before and prints one line on stderr recommending it. The tools and their schemas are unchanged.

Install this release

This is a GitHub source release. npm and MCP Registry versions are published separately. The commands below select this exact version; unpinned npx examples later in this document select the version currently available on npm.

git clone --branch v2.1.0 --depth 1 https://github.com/get-mcp-ads/google-analytics-mcp-server.git
cd google-analytics-mcp-server
npm ci
npm run build

Configure your MCP client to run node with the absolute path to dist/cli.js and the platform credentials documented below.

Prefer a managed connection? Use Google Analytics 4 with hosted getmcpads. Connect your account, select the data your assistant may access and use the hosted MCP connection. See the site for current features and plans.

What you get

27 read toolsReports, pivots, funnels, realtime, plus the Admin API: properties, data streams, custom definitions, key events, audiences
DiagnosticsEcommerce, BigQuery export, server-side tagging, audience exports, quota snapshots
51 metrics, 62 dimensionsWith a compatibility matrix that catches invalid combinations before they hit the API
6 resourcesLive catalogues the model can read: metrics, dimensions, compatibility rules, 12 workflow recipes
Identifier redactionUser, email and device identifiers redacted by default on access bindings and audience exports, with explicit opt-in to see them
No writes at allNot a flag, a property of the code. See below
Compatibility, checked before the call

GA4 rejects many metric and dimension combinations, and its errors rarely explain which pair is at fault. This server carries the compatibility matrix, so ga4_check_compatibility and ga4_validate_query let the model verify a combination before spending a call and a quota token on it.

Quotas matter here more than on ad platforms: GA4 charges tokens per property per day, and a few careless exploratory queries can exhaust them. ga4_get_property_quotas_snapshot shows what is left.


Read-only, and why it stays that way

There are no write tools, and no environment variable that adds any. Every tool calls a read method of the Data API or the Admin API.

This is not caution for its own sake. A misread report is a wrong answer you can spot. A mistaken write to an analytics property, a deleted audience or an edited data stream, corrupts the record you use to judge everything else, and often silently. The other servers we publish do have write tools, guarded by a mandatory preview. This one has none.

Our ad platform servers with guarded writes: Meta Ads · Google Ads · TikTok Ads


Personal data

Analytics data is not anonymous by default. A GA4 property can carry a userId you set yourself, a device identifier, or a Google Signals pseudonymous ID. An MCP conversation sends whatever a tool returns to a model.

Identifiers are redacted by default wherever this server can return them, and showing them is an explicit opt-in, never the default.

ToolBehaviour
ga4_list_admin_resourcesAccess bindings have user and email identifiers redacted
ga4_query_audience_exportIdentifier columns redacted, matched against the export's own dimension metadata
ga4_get_audience_export_diagnosticsSame redaction on the row sample

Every one of these accepts includePersonalIdentifiers: true to return raw values, and defaults to false.

Audience export rows are positional, so the redaction reads the export's dimension metadata to find identifier columns. If that metadata is missing, every value in the row is redacted rather than guessing which column is safe. Failing closed is the point.

Report rows are not redacted. ga4_run_report and the other reporting tools return what you asked for. Altering the numbers a report returns would be worse than returning them.

So one decision stays yours: if your property carries a userId you consider personal, do not request it as a report dimension in a conversation whose transcript leaves your machine.


Getting credentials

Three values, obtained once.

1. OAuth client

In a Google Cloud project, enable the Google Analytics Data API and the Google Analytics Admin API, then create an OAuth client under APIs & Services → Credentials. Choose Desktop app for local use. Note the client ID and client secret.

2. Refresh token

Run the OAuth consent flow once, signed in as a Google account with access to your GA4 properties, and keep the refresh token. The analytics.readonly scope is enough, and it is the only one you should grant.

📖 Google OAuth for installed apps

The refresh token does not expire. It is the sensitive value: anyone holding it can mint access tokens indefinitely. Use an OAuth client dedicated to this server so you can revoke it on its own.

3. Property ID, optional

Set GA4_PROPERTY_ID to avoid passing it on every call. Find it in GA4 under Admin → Property Settings, or list them with ga4_list_properties.

Run ga4_health_check as your first call. It verifies the credentials and lists the properties you can actually reach, without printing any secret.


Setup

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "google-analytics": {
      "command": "npx",
      "args": ["-y", "@getmcpads/google-analytics-mcp-server"],
      "env": {
        "GA4_CLIENT_ID": "your-client-id",
        "GA4_CLIENT_SECRET": "your-client-secret",
        "GA4_REFRESH_TOKEN": "your-refresh-token",
        "GA4_PROPERTY_IDS": "123456789"
      }
    }
  }
}

Restart Claude Desktop. Ask it: "list my Google Analytics properties".

Claude Code
claude mcp add google-analytics --env GA4_CLIENT_ID=... --env GA4_CLIENT_SECRET=... --env GA4_REFRESH_TOKEN=... -- npx -y @getmcpads/google-analytics-mcp-server
Cursor

.cursor/mcp.json in your project, same shape as the Claude Desktop config above.

From source
git clone https://github.com/get-mcp-ads/google-analytics-mcp-server.git
cd google-analytics-mcp-server
npm install && npm run build
cp .env.example .env   # then fill in your credentials
npm start
Configuration
VariableDefaultMeaning
GA4_CLIENT_IDnoneRequired. OAuth client ID
GA4_CLIENT_SECRETnoneRequired. OAuth client secret
GA4_REFRESH_TOKENnoneRequired. From the consent flow
GA4_PROPERTY_IDnoneOptional default, saves passing it on every call
GA4_PROPERTY_IDSunsetRecommended. Comma-separated property IDs every tool is limited to. Unset, every property the credentials reach is available. Required in 3.0.0
LOG_LEVELinfodebug, info, warn, error

Check your setup at any time:

npm run doctor

Tools

Every tool is listed below. See server-card.json for complete parameter and output schemas.

27 read tools

ToolPurpose
ga4_health_checkRead-only GA4 health check.
ga4_list_propertiesList all GA4 properties accessible with the current credentials.
ga4_run_reportRun a GA4 analytics report with intelligent query planning.
ga4_run_realtime_reportRun a read-only GA4 Data API realtime report.
ga4_get_metadataGet the complete list of dimensions and metrics available for a specific GA4 property.
ga4_get_custom_definitionsList custom dimensions and custom metrics exposed by GA4 Data API metadata.
ga4_get_key_eventsInventory GA4 key events/conversions using metadata-aware Data API reports.
ga4_get_ecommerce_diagnosticsRead-only ecommerce coverage diagnostics for core ecommerce events, revenue metrics, and item-level reporting over a date range.
ga4_get_event_parametersBest-effort event parameter inventory from GA4 metadata plus event reports.
ga4_run_funnel_recipeRun a read-only configurable funnel recipe using one GA4 report per eventName/pagePath step and return simple step counts.
ga4_get_audience_export_diagnosticsRead-only Audience Export diagnostics.
ga4_get_audience_diagnosticsRead-only audience diagnostics from Admin API audiences, Data API recurring audience lists, and observed audienceName report fallback.
ga4_get_bigquery_export_diagnosticsDetect GA4 BigQuery export links and diagnose export modes, stream coverage, excluded events, and dataset location.
ga4_get_server_side_tagging_diagnosticsBest-effort read-only server-side tagging diagnostics from data streams, Measurement Protocol secrets, event rules, and stream settings.
ga4_run_advanced_funnel_reportRun the GA4 Data API v1alpha runFunnelReport endpoint with optional breakdown/next-action, falling back to read-only step counts if unavailable.
ga4_get_channel_groupsList custom channel groups defined for a GA4 property.
ga4_validate_queryValidate a metric/dimension combination BEFORE executing.
ga4_run_pivot_reportRun a read-only GA4 Data API pivot report with native filters, ordering, quota state, multiple date ranges, and up to 250,000 pivot cells.
ga4_batch_run_reportsRun 1-5 independent read-only GA4 Core reports for the same property in one official Data API batch request.
ga4_batch_run_pivot_reportsRun 1-5 independent read-only GA4 pivot reports for the same property in one official Data API batch request.
ga4_check_compatibilityAsk the official GA4 Data API which dimensions and metrics are compatible with a proposed Core report selection.
ga4_get_property_quotas_snapshotRead the current GA4 Data API property quota snapshot from the official v1alpha endpoint.
ga4_list_accountsList raw GA4 Analytics Admin accounts accessible to the authenticated user (read-only, auto-paginated).
ga4_list_admin_resourcesList an allowlisted GA4 Admin collection in read-only mode: streams, custom definitions, key events, audiences, product links, annotations, channel groups, expanded datasets, subproperty/rollup configuration, and access bindings.
ga4_get_property_configurationRead GA4 property details plus selected singleton Admin settings (attribution, retention, Google Signals, reporting identity, or user-provided-data settings).
ga4_list_audience_exportsList existing GA4 Audience Export snapshots and Recurring Audience Lists without creating new exports.
ga4_query_audience_exportQuery rows from an existing GA4 Audience Export.

6 resources

URIContents
ga4://manifestWhat this server exposes, and which tool to run first
ga4://metricsAll 51 metrics with categories and formats
ga4://dimensionsAll 62 dimensions and where they are valid
ga4://compatibilityThe compatibility matrix
ga4://recipes12 step-by-step workflows
ga4://p2-diagnosticsDiagnostic playbooks

Security

  • The client secret and refresh token are never logged, at any log level, or written to disk.
  • A revoked refresh token is reported once. When Google answers invalid_grant, every later call returns the same message with the steps to authorize again, and the server stops asking Google for a token until it restarts.
  • Properties can be limited. With GA4_PROPERTY_IDS set, a call naming another property is refused before any request, and discovery lists only the allowed properties.
  • Three hosts are contacted, and only three: analyticsdata.googleapis.com, analyticsadmin.googleapis.com and oauth2.googleapis.com. A test fails the build if a fourth host appears in the source.
  • No fetch follows a redirect. Every outbound call sets redirect: "error", so a redirect cannot forward a bearer token or client secret to another host. A test fails the build if any fetch omits this.
  • No telemetry. The server makes no network call other than to Google.

Full policy, including how personal data is handled: SECURITY.md.


Looking for a managed, multi-platform version?

Try hosted GA4 if you want to use this source without operating a local server. getmcpads also connects advertising, Search Console and GA4 through one MCP URL. Source availability and plan limits are listed on the site; connecting an account is still required.

  1. Follow the GA4 connection guide.
  2. Select the account or property your assistant may read.
  3. Connect Claude, ChatGPT or Codex.
  4. Try a read-only review: “Compare acquisition channels, landing pages and configured key events. State missing data and do not change anything.”

See the current hosted tool catalogue and pricing before choosing a paid plan. This Apache 2.0 adapter remains independently useful with your own credentials.


Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md. Please read SECURITY.md before reporting anything security-related.

Licence

Apache License 2.0. See also NOTICE.

Google, Google Analytics and GA4 are trademarks of Google LLC. This project is not affiliated with, endorsed by, or sponsored by Google LLC. It is an independent client of a public API.

MCP contracts and desktop bundle

Every tool declares read/write annotations, parameter descriptions and a structured output schema. Successful calls expose the payload as structuredContent.result; errors retain isError: true. The generated server card contains definitions only.

Run npm run bundle -- /path/to/output to build a .mcpb desktop bundle from the current catalog. Credentials are entered locally during installation. This server remains read-only.

More from getmcpads

Meta Ads · Google Ads · Google Search Console · TikTok Ads · Pinterest Ads · X Ads

Maintained by Emmanuel at getmcpads. Questions: hello@getmcpads.com.

Questions fréquentes

Qu'est-ce que Google Analytics 4 ?

Google Analytics 4 MCP server: 27 read tools, no write tools.

Comment installer Google Analytics 4 ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add google-analytics-4 -e 'GA4_CLIENT_ID=<GA4_CLIENT_ID>' -e 'GA4_CLIENT_SECRET=<your ga4_client_secret>' -e 'GA4_REFRESH_TOKEN=<your ga4_refresh_token>' -e 'GA4_PROPERTY_ID=<GA4_PROPERTY_ID>' -e 'GA4_PROPERTY_IDS=<GA4_PROPERTY_IDS>' -- npx -y @getmcpads/google-analytics-mcp-server@2.1.1. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour Google Analytics 4 ?

Oui. Il attend GA4_CLIENT_ID, GA4_CLIENT_SECRET, GA4_REFRESH_TOKEN, à renseigner dans sa configuration.

Google Analytics 4 est-il open source ?

Oui. Son code est sur GitHub sous licence Apache-2.0.

Qui maintient Google Analytics 4 ?

Il est publié par get-mcp-ads. 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.