Skip to main content
Glama
dienhokhanh

ga4-mcp-server

by dienhokhanh

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_accountsA

List the Google Analytics accounts the authenticated user can access, each with its GA4 properties (ID and display name). Start here when you don't know the property ID.

list_propertiesA

List accessible GA4 properties as a flat list. Optionally filter by account (ID or name) or by a case-insensitive search on the property name.

get_propertyA

Get a GA4 property's settings: time zone, currency, industry category, service level (Standard/360), creation time and parent account.

list_data_streamsB

List a property's data streams (web, Android, iOS) including measurement IDs (G-XXXX), website URLs and app IDs.

get_metadataA

List the dimension and metric API names available for reports on a property, including the property's custom dimensions/metrics (e.g. customEvent:plan_type). Use search to narrow the list — the full catalogue is large.

check_compatibilityA

Check whether a set of dimensions and metrics can be used together in one report. Returns the incompatible fields (if any). Use before run_report when mixing scopes, e.g. item-scoped with session-scoped fields.

run_reportA

Run a Google Analytics 4 report (Data API runReport). Returns rows as JSON records keyed by dimension/metric name. Examples: traffic by channel, top pages, conversions by campaign, revenue by country, daily trend with dimension "date".

batch_run_reportsA

Run up to 5 reports for one property in a single API call (cheaper and faster than separate run_report calls). Each request takes the same fields as run_report.

run_pivot_reportB

Run a pivot (cross-tab) report. Every dimension must appear in exactly one pivot's fieldNames. Example: pivots [{fieldNames:["country"],limit:5},{fieldNames:["deviceCategory"],limit:3}] with metric sessions.

run_realtime_reportA

Report on events from the last 30 minutes (up to 60 for GA4 360). Realtime supports a limited set of fields, e.g. dimensions country, city, deviceCategory, unifiedScreenName, eventName, minutesAgo; metrics activeUsers, eventCount, keyEvents, screenPageViews.

list_custom_dimensionsA

List a property's custom dimensions (parameter name, display name, scope). In reports they're referenced as customEvent:, customUser: or customItem:.

list_custom_metricsB

List a property's custom metrics (parameter name, display name, unit, scope).

list_key_eventsB

List a property's key events (formerly called conversions), with counting method and creation time.

list_audiencesA

List a property's audiences (uses the v1alpha Admin API). By default returns a summary; set includeDefinitions for full filter clauses.

Prompts

Interactive templates invoked by user choice

NameDescription
weekly_traffic_summarySummarise the last 7 days vs. the previous 7 days.
top_landing_pagesFind the best and worst performing landing pages.
channel_performanceCompare acquisition channels on volume, engagement and conversion.

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 14 tools

Disambiguation4/5

Tools are mostly distinct by resource and action, but get_metadata overlaps with list_custom_dimensions/list_custom_metrics for custom fields, and list_accounts/list_properties both surface property information. Descriptions help clarify the intended use, so misselection is unlikely but possible.

Naming Consistency5/5

All names follow a consistent snake_case verb_noun pattern (list_*, get_*, run_*, check_*, batch_run_*). There is no mixing of casing or verb styles, making the set predictable and easy to navigate.

Tool Count5/5

With 14 tools, the server comfortably covers the GA4 reporting and metadata surface without feeling bloated. Each tool maps to a meaningful operation and the count falls within a well-scoped range.

Completeness4/5

The read/query surface is strong, covering accounts, properties, streams, metadata, compatibility checks, multiple report types, custom dimensions/metrics, key events, and audiences. However, admin write operations (create/update/delete) and some report types like funnel reports are absent, leaving minor gaps for full GA4 lifecycle coverage.

Maintenance

ActivityMaintained
ResponsivenessNo issues