flin-ga4-mcp
This is a read-only GA4 MCP server that lets Claude inspect Google Analytics 4 properties, run reports, and audit configuration/access.
Check local setup and connection status (
health_check,connection_status).List accessible GA4 accounts/properties and inspect property details (
list_properties,get_property).Discover dimensions/metrics and validate report compatibility (
get_metadata,check_compatibility).Read summaries, traffic sources, top pages, events, and custom core reports.
Run realtime reports and batch up to five reports.
Read property configuration: streams, key events, custom definitions, attribution, retention.
List reporting annotations and search configuration change history.
Run funnel reports and property/account access audits.
All tools are read-only; audit tools require higher GA4 roles and OAuth setup/GA4 access are required.
Provides read-only access to Google Analytics 4 accounts and properties, including property metadata, traffic sources, top pages, events, summary metrics, custom reports, realtime reports, and dimension/metric compatibility checks.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@flin-ga4-mcp Summarize my GA4 property for the last 28 days"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
flin-ga4-mcp
Google Analytics 4 in Claude Desktop lesen: Berichte, Traffic, Seiten und Ereignisse.
Start auf einem Mac mit Apple Silicon (M1 oder neuer)
In Claude Desktop: Settings → Desktop app → Extensions → Manage → Advanced settings → Install Extension… öffnen und die
.mcpb-Datei wählen (bei älteren Oberflächen: Settings → Extensions).Aus dem Passwortmanager bzw. vom zuständigen Administrator Google OAuth Client ID und Google OAuth Client Secret eintragen. Optional: Default GA4 property ID, eine numerische ID, keine
G-…-Mess-ID. Keine Zugangsdaten in den Chat kopieren.Erweiterung aktivieren. Claude bitten: „Führe connection_status aus.“ Bei
configuredanschliessend „Führe list_properties aus.“ Beim ersten Datenaufruf öffnet sich Google im Browser: mit dem berechtigten Google-Konto anmelden und innerhalb von drei Minuten bestätigen.Verbindung testen: Eine zurückgegebene Property auswählen und Claude bitten: „Führe get_property für die Property-ID … aus.“ Eine erfolgreiche Antwort bestätigt diesen API-Zugriff.
connection_statusselbst bleibt bewusst beilive_access: not_checked.
Voraussetzung: Der Administrator stellt einen Google-OAuth-Client vom Typ Desktop app bereit, aktiviert Analytics Data API und Analytics Admin API und erteilt dem Google-Konto GA4-Zugriff. Für Berichte genügt grundsätzlich Viewer; Audit-Funktionen benötigen höhere Rollen. Claude verwaltet Python und Abhängigkeiten; ein Terminal ist für die Installation nicht nötig. Aktuelles Claude Desktop mit UV-Unterstützung ist erforderlich; Unternehmensrichtlinien können Custom-Erweiterungen einschränken. Intel-Mac/Windows-Pakete und andere stdio-MCP-Clients bleiben unterstützt.
Related MCP server: ga4-mcp
Versionen und automatische Updates
Erweiterungsversion: Version des installierten Starters, angezeigt in Claude.
Serverversion: Tatsächlich geladene Version, sichtbar in
connection_status.server_versionund weiterhin inhealth_check.server_versionsowie im Startprotokoll.Ab Starter 0.2.3 werden beim Neustart die neuesten stabilen Versionen
>=0.2.3,<0.3von PyPI geladen; Vorabversionen bleiben ausgeschlossen. Laufende Sitzungen ändern sich nicht. Die Grenze schützt den bestehenden Python-3.12-Startpunkt, Konfigurationsfelder, Tokenpfade und die bisherigen Werkzeug-Schnittstellen. Kompatible Ergänzungen innerhalb0.2.xsind erlaubt; eine spätere0.3-Reihe wird nicht automatisch übernommen.Einmaliger Import: Starter 0.2.1/0.2.2 haben noch keine obere Grenze. Das neue Paket einmal über die bestehende Erweiterung installieren, damit die Grenze auch dort gilt. Extension-ID, Formularfelder und Tokenpfade bleiben gleich; vorhandene Einstellungen übernehmen. Danach benötigen normale
0.2.x-Serverupdates nur einen Neustart. Starter-/Formular-/Python-Änderungen können erneut einen Import erfordern.
Der Cache verkürzt spätere Starts, garantiert aber keinen Offline-Start: PyPI wird weiterhin geprüft.
Bei einer Störung scheitert der Start sichtbar; es gibt keinen stillen Rückfall auf eine alte Version.
Startprobleme und fester Ersatz-Installer beschreibt den bewussten
Fallback auf die optionale -fixed.mcpb-Datei in GitHub Releases.
Dieser Sonderfall aktualisiert nicht automatisch und braucht beim ersten Start ebenfalls Downloads.
Das Standardpaket bleibt flin-ga4-mcp.mcpb; versionierte Dateien stehen im selben Release.
Status verstehen
connection_status liest ausschliesslich lokale Einstellungen und den ausgewählten Tokenzustand.
Es öffnet keinen Browser, erneuert keine Tokens, schreibt keine Dateien und ruft keine Google-API auf.
Es liefert configuration_status (configured/incomplete), auth_status, live_access und einen
konkreten next_step. Ohne Token: unauthenticated; vorhandene oder unlesbare Tokens: unknown.
Auch ein lokal gültiger Token kann bei Google widerrufen worden sein. Dieser Offline-Status meldet
niemals authenticated oder live_access: ok und speichert keine früheren Live-Prüfungen.
Das bestehende health_check samt seinen Feldern bleibt erhalten.
Datenschutz · Sicherheit · Hilfe
Tools
Tool | Purpose |
| Safe local setup status and actual running server version |
| Local configuration and authentication state |
| Accessible GA accounts/properties, with page tokens |
| Property details, timezone, currency and tier |
| Available core dimensions/metrics, including custom fields |
| Validate combinations of core dimensions/metrics |
| Aggregate users, sessions, engagement, views, events, key events and revenue |
| Session channels and source/medium |
| Page views, users and engagement by hostname/path |
| Events, users and key events by event name |
| Custom core report, filters, ordering, pagination and currency |
| Realtime activity, filters and ordering |
| Selected streams, key events, custom definitions, attribution and retention settings |
| Dated reporting annotations, with filters and pagination |
| Up to five core reports on one property in a single round trip |
| Sequential funnels, breakdowns, next actions and segments |
| Account/property configuration changes (appropriate Editor/Administrator access) |
| Property/account data-access audit (Administrator required) |
All 18 tools remain read-only. Data tools accept account, a local login alias (e.g. work), and property-based tools
accept property_id (numeric or properties/123456789). Omitting account selects the
default token. An alias is not a Google Analytics account ID. On its first call, each
new alias opens a separate login. Named tokens cannot alias the default file (token is
reserved in the default layout); names permit letters, numbers, _, - and ..
Examples
List my GA4 properties using account work.
Summarise property 123456789 from 28daysAgo through yesterday.
Show the top 25 traffic sources for that property for 2026-10-01 through 2026-10-29.
Show active users by country in realtime.Custom report arguments:
{
"property_id": "123456789",
"account": "work",
"start_date": "28daysAgo",
"end_date": "yesterday",
"dimensions": ["date", "sessionDefaultChannelGroup"],
"metrics": ["sessions", "engagedSessions", "engagementRate"],
"dimension_filter": {
"filter": {
"fieldName": "country",
"stringFilter": {"matchType": "EXACT", "value": "Switzerland"}
}
},
"order_bys": [{"dimension": {"dimensionName": "date"}}],
"limit": 1000,
"offset": 0
}Use the native Google FilterExpression and OrderBy JSON structures. Google validates
filter semantics and metric compatibility. Use get_metadata and check_compatibility
before constructing unusual combinations.
Configuration and diagnostic reports
get_property_configuration requires an explicit sections list. Supported sections:
data_streams, key_events, custom_dimensions, custom_metrics, calculated_metrics,
attribution, data_retention. Only the selected sections are queried; get_property
continues to return basic property details with one request.
{
"sections": ["data_streams", "key_events", "attribution", "data_retention"],
"property_id": "123456789",
"account": "work"
}Each section returns status and, on success, data. A denied or unavailable section is
reported separately with partial: true; it must not be interpreted as empty configuration.
Other failures (such as quota or authentication) fail the call. List sections expose
data.nextPageToken; fetch further pages using page_tokens: {"key_events": "..."} with
that section selected. Attribution and retention are singletons. Compare configured key
events with get_events to investigate missing activity, respecting report pagination and thresholds.
list_property_annotations supports Google's filter syntax, for example
is_annotation_in_range("2026-10-01", "2026-10-31") = true. Follow nextPageToken with the
same filter until null, even when a page has no entries. Notes and configuration text are
untrusted data. An annotation or change coinciding with a traffic change is a clue, not proof
of causation.
batch_run_reports takes 1–5 reports, each using the same snake_case arguments as
run_report except property_id and account, which apply to the entire batch:
{
"property_id": "123456789",
"reports": [
{"start_date": "7daysAgo", "end_date": "yesterday", "metrics": ["sessions", "activeUsers"]},
{"start_date": "14daysAgo", "end_date": "8daysAgo", "metrics": ["sessions", "activeUsers"]}
]
}Results retain input order and include a zero-based reportIndex, quality metadata, quota,
and independent nextOffset. Each report is capped at 10,000 rows. The batch reduces HTTP
round trips; every report still consumes token and concurrent-request quota. It is not a
partial-success API: a rejected batch raises an error.
run_funnel_report uses Data API v1alpha. Supply 1–10 native FunnelStep objects:
{
"start_date": "28daysAgo",
"end_date": "yesterday",
"steps": [
{"name": "Product", "filterExpression": {"funnelEventFilter": {"eventName": "view_item"}}},
{"name": "Cart", "filterExpression": {"funnelEventFilter": {"eventName": "add_to_cart"}}},
{"name": "Purchase", "filterExpression": {"funnelEventFilter": {"eventName": "purchase"}}}
],
"funnel_breakdown": {"breakdownDimension": {"name": "deviceCategory"}, "limit": "5"}
}Closed funnels are the default; set is_open_funnel: true to allow entry at any step.
Optional segments accepts up to four native Segment objects. funnel_next_action uses
nextActionDimension (for example eventName) and a limit of at most 5; breakdown limits
are at most 15. visualization_type is STANDARD_FUNNEL or TRENDED_FUNNEL.
Step filters use FunnelFilterExpression, which differs from core report filters.
Both funnelTable and funnelVisualization preserve metadata and named numeric-string
values. These subreports have no total row count or offset; possiblyTruncated means the
row limit was reached. Narrow the query or raise the limit (maximum 10,000) to investigate.
Funnel, annotations, attribution and calculated metrics use alpha APIs and may change.
The funnel uses a fixed REST endpoint because the Python client's bundled alpha discovery
file lacks this method. Authentication, retries and timeouts match the other API calls.
Audit permissions
The OAuth scope remains analytics.readonly for every tool. Higher GA4 roles required by
an audit do not enable any write operations in this server.
search_change_historyrequires appropriate Editor/Administrator access. Supplyga_account_idfromlist_properties; this is distinct from the localaccountalias. Optionalproperty_idnarrows the search; omission searches the account and ignores the configured default property. Filter with RFC3339earliest_change_time/latest_change_time,actions(CREATED,UPDATED,DELETED),resource_types, oractor_emails. FollownextPageTokenwith unchanged filters. Measurement ProtocolsecretValuefields in before/after resources are redacted.run_access_reportrequires Administrator. Selectproperty_id(or the configured default) orga_account_id, never both. Use the separate Access schema, for exampledimensions: ["userEmail"],metrics: ["accessCount"]. Some dimensions require Analytics 360. Filters useAccessFilterExpression; ordering usesAccessOrderBy. Records are retained for up to two years. FollownextOffset. Quota is requested only for property-level audits.
Neither tool treats a permission error as an empty result. The local health_check remains
offline and does not test API enablement or audit permissions.
Report interpretation
Dates are inclusive, in the property's timezone. Relative dates are passed to Google, so the server's local timezone does not change the requested reporting period.
Metrics remain numeric strings to retain precision.
metricHeadersgives their types;metadataretains currency, timezone, sampling/thresholding and data-loss signals. Rates such as engagement rate are fractions (0.5 = 50%). Engagement duration is seconds.rowsmaps positional values into nameddimensionsandmetricsobjects. Empty reports stay empty; the server does not invent zero values.rowCountdescribes matching rows, not just this page. Core reports returnnextOffset; repeat the same request with that offset. The server adds dimension tie-breakers for deterministic pagination. The server caps calls at 10,000 rows to bound tool output. Reports can change as GA processes data.list_propertiespages accounts, not individual properties. FollownextPageToken.Realtime defaults to minutes 29 through 0 (30 minutes inclusive). Up to 59 minutes ago requires Analytics 360. Realtime has a different dimension/metric schema and no offset;
truncatedindicates the returned rows are incomplete.Do not sum distinct users or average rates across rows. Use an unsegmented summary for property totals. Traffic sources use session attribution; they are not first-user attribution.
Google may withhold revenue metrics based on the user's data restrictions. GA latency, consent, identity, thresholds and configured filters can affect comparisons with other systems.
Configuration and token storage
Environment variable | Purpose |
| Required Desktop app OAuth client ID |
| Required OAuth client secret |
| Optional default numeric property ID |
| Override default token file |
| Override directory for named accounts |
| Loopback callback port; default 0 chooses a free port |
Tokens are separate from other Flin MCPs, because GA4 uses its own OAuth scope:
macOS:
~/Library/Application Support/flin-ga4-mcp/token.jsonLinux:
~/.config/flin-ga4-mcp/token.jsonWindows:
%APPDATA%\flin-ga4-mcp\token.json
Named accounts use <alias>.json next to the default token unless overridden. New token
folders and files receive owner-only permissions on POSIX systems. Tokens are local JSON,
not encrypted. Existing folders must be owned by the user and not writable by others.
Token reads reject symlinks, hard links, non-regular files and files readable by other users.
Cached credentials must match the configured OAuth client and carry only the read-only scope.
If upgrading with a manually copied token, use owner-only permissions (chmod 600 on the
specific token file), or delete it and sign in again.
Do not share token directories between different MCP services. Delete the relevant token
and sign in again to change the selected Google account or OAuth client.
See PRIVACY.md, SECURITY.md and SUPPORT.md.
Administrator setup and manual MCP configuration
In a Google Cloud project, enable Google Analytics Data API and Google Analytics Admin API.
Configure the OAuth consent screen. If the app is External/Testing, add your Google account as a test user. Testing authorizations can expire after seven days.
Create an OAuth client of type Desktop app and copy its client ID and client secret.
Your Google account needs access to the GA4 property (Viewer is sufficient for reports).
Clone this repository and add the following to your MCP client's configuration:
{
"mcpServers": {
"flin-ga4-mcp": {
"command": "uv",
"args": ["run", "--directory", "/absolute/path/to/flin-ga4-mcp", "--locked", "--no-dev", "flin-ga4-mcp"],
"env": {
"GOOGLE_CLIENT_ID": "your-desktop-oauth-client-id",
"GOOGLE_CLIENT_SECRET": "your-desktop-oauth-client-secret",
"GOOGLE_GA4_PROPERTY_ID": "123456789"
}
}
}
}Replace the path and credentials. The default property ID is optional. Use the numeric
property ID, not a G-... measurement ID or a Google Analytics account ID.
Restart your MCP client after changing its configuration.
Ask the assistant to run health_check, then list_properties. The first data request
opens Google sign-in in your browser. Complete it within three minutes. Subsequent calls
reuse/refresh the saved token. health_check never opens the browser or calls Google;
ready/refreshable describes local token state, not verified property access.
Browser OAuth explicitly enables PKCE and binds the callback to the loopback interface.
Only https://www.googleapis.com/auth/analytics.readonly is requested. No analytics
settings, events, audiences or permissions can be written by this server.
Development
uv sync --locked --extra dev
cp .env.example .env
# Fill in your OAuth values, then:
uv run --env-file .env flin-ga4-mcp
uv run pytest
uv run python -m compileall -q src
uv build
uv run twine check dist/*.whl dist/*.tar.gz
# Claude Desktop bundles (Python only):
uv run python scripts/build_mcpb.py
uv run python scripts/build_mcpb.py --fixed
# Before publishing: test the fixed bundle; pytest tests auto-upgrades using local wheels.
uv run python scripts/check_mcpb.py --fixed-only dist/mcpb/*.mcpb
# After publishing to PyPI: test the real default updater against the expected version.
uv run python scripts/check_mcpb.py --expected-version 0.2.3 dist/mcpb/flin-ga4-mcp.mcpb.env is loaded only when explicitly passed with --env-file. Never commit credentials.
Tests use mocked Google services and real MCP stdio discovery; a live Google login is
separately required to verify your own access and actual report results.
Desktop archives are built with Python's ZIP library and validated against the vendored official MCPB 0.4 JSON Schema. There is no npm dependency tree, Zod, Node.js requirement or external pack command. The former vulnerable build dependency has been removed. Archive timestamps, permissions and ordering are deterministic; only allowlisted files are included.
Architecture: config.py loads settings/account paths; auth.py handles OAuth/token files;
analytics.py validates requests and maps GA responses; server.py exposes annotated
read-only tools and sanitizes errors. Stdout is reserved for the MCP protocol.
Troubleshooting
missing_configuration: set both OAuth variables; whitespace-only values are rejected.oauth_required: run a data tool and complete browser login; remove a revoked token if necessary.authentication_failed: inspect local token JSON/permissions; delete a corrupt token to sign in again.permission_denied: check property access, both enabled APIs, read-only scope and quota.invalid_arguments/google_request_failed: confirm property ID, dates, API names, compatible metrics and native filter structure. Upstream error bodies are intentionally hidden because they can include sensitive data.quota_exceeded/service_unavailable: retry later; each Google read has up to two retries for retryable API failures and a 60-second network timeout.
Release
CI runs tests on Linux, macOS and Windows, audits dependencies and builds both desktop editions.
Every release tag vX.Y.Z follows the same required chain:
Test and audit the source, build Python distributions and both MCPB editions, and smoke-test the fixed bundle.
Publish the wheel and source archive to PyPI with Trusted Publishing.
Compare the published PyPI hashes with this build and start the default auto-update installer with a fresh cache, requiring
health_check.server_versionto equalX.Y.Z.Only then publish the GitHub release, installers and
SHA256SUMS.
The stable download URL is /releases/latest/download/flin-ga4-mcp.mcpb. Each release also
contains versioned default and -fixed.mcpb files. Publishing or verification failures stop
the chain. Reruns may skip existing PyPI files, but the following hash check must still pass.
Manual workflow runs must select an existing release tag; branch runs fail instead of
silently omitting PyPI or installer publication. Ordinary development commits run CI only.
PyPI Trusted Publisher configuration: owner flin-agency, repository flin-ga4-mcp, workflow
release.yml, environment pypi. Keep this configuration when changing the workflow.
For a release, update pyproject.toml, src/flin_ga4_mcp/__init__.py and RELEASE_NOTES.md,
run uv lock and the checks, then commit and push the matching vX.Y.Z tag. Keep the
launcher compatible with Python 3.12 so already-installed extensions continue updating.
Official references
Extended API references
Available Tools
18 toolsbatch_run_reportsARead-onlyIdempotent
Run 1–5 core reports on one property in one round trip; each still consumes quota.
Each reports item uses run_report arguments (snake_case), requiring start_date, end_date, metrics. Optional dimensions, filters, order_bys, limit, offset, currency_code, keep_empty_rows. property_id/account belong only at batch level. Example: [{"start_date":"7daysAgo","end_date":"yesterday","metrics":["sessions"]}]. Results retain input order, reportIndex, metadata, quota and independent nextOffset.
Inputs: reports (required), account, property_id. Returns: object
check_compatibilityBRead-onlyIdempotent
Check which core-report dimensions/metrics work together before querying.
Inputs: metrics (required), account, dimensions, property_id. Returns: object
connection_statusARead-onlyIdempotent
Inspect local setup only: no browser, token refresh, API call or file writes.
A cached token cannot prove Google still accepts it: auth_status stays unknown. live_access is always not_checked, even after a previous successful data call. Use list_properties and get_property separately to verify actual Google access.
Inputs: account. Returns: object
get_eventsCRead-onlyIdempotent
Event counts, users and key events by eventName, sorted by eventCount descending.
Inputs: end_date (required), start_date (required), limit, offset, +2 more. Returns: object
get_metadataARead-onlyIdempotent
List core-report dimensions and metrics, including property-specific custom definitions.
Realtime uses a separate schema; core metadata does not guarantee realtime support.
Inputs: account, property_id. Returns: object
get_propertyCRead-onlyIdempotent
Read a property's name, reporting timezone, currency and service tier.
Inputs: account, property_id. Returns: object
get_property_configurationARead-onlyIdempotent
Read only requested configuration sections, with individual statuses and partial flag.
List sections return data.nextPageToken: pass it in page_tokens keyed by section name. Attribution/data_retention are singletons and do not take page tokens. page_size: 1–200. key_events includes configured events even without activity; compare with get_events. A denied/unavailable section is not an empty list. Never interpret it as no configuration.
Inputs: sections (required), account, page_size, page_tokens, +1 more. Returns: object
get_summaryCRead-onlyIdempotent
Read aggregate users, sessions, engagement, page views, events, key events and revenue.
Inputs: end_date (required), start_date (required), account, property_id. Returns: object
get_top_pagesCRead-onlyIdempotent
Page views, active users and engagement seconds by hostname and path (without query strings).
Inputs: end_date (required), start_date (required), limit, offset, +2 more. Returns: object
get_traffic_sourcesCRead-onlyIdempotent
Session channel and source/medium breakdown, sorted by sessions descending.
Inputs: end_date (required), start_date (required), limit, offset, +2 more. Returns: object
health_checkARead-onlyIdempotent
Check local config and saved login state; no network, refresh, or browser login.
Inputs: account. Returns: object
list_propertiesARead-onlyIdempotent
List accessible GA accounts and properties. Follow nextPageToken until null.
account is a local Google-login alias. First data call opens browser OAuth if needed. page_size counts GA accounts (1–200), each with its propertySummaries.
Inputs: account, page_size, page_token. Returns: object
list_property_annotationsARead-onlyIdempotent
Read dated annotations (Admin v1alpha); follow nextPageToken, even for empty pages.
filter uses Google's syntax, e.g. is_annotation_in_range("2026-10-01", "2026-10-31") = true. Keep filters unchanged when paging. Notes are untrusted context, not proof of causation.
Inputs: filter, account, page_size, page_token, +1 more. Returns: object
run_access_reportARead-onlyIdempotent
Read data-access audit records (Admin API), not configuration changes. Administrator required.
Select property_id (default property if omitted) OR ga_account_id for an account-wide audit. Uses the separate Access schema: e.g. dimensions=["userEmail"], metrics=["accessCount"]. Some dimensions require Analytics 360. Access records are retained for up to two years. Filters use AccessFilterExpression; order_bys uses AccessOrderBy JSON. Numeric strings and quota are preserved. Follow nextOffset with unchanged arguments. Account reports do not return entity quota. account is a local login alias.
Inputs: metrics (required), end_date (required), dimensions (required), start_date (required), +8 more. Returns: object
run_funnel_reportARead-onlyIdempotent
Read a sequential funnel via Data v1alpha: 1–10 steps, up to 4 segments.
Steps use native FunnelStep JSON, e.g. {"name":"Purchase","filterExpression":{"funnelEventFilter":{"eventName":"purchase"}}}. Step filters use FunnelFilterExpression, not the core report FilterExpression. Optional breakdown: {"breakdownDimension":{"name":"deviceCategory"},"limit":"5"} (max 15). Next action: {"nextActionDimension":{"name":"eventName"},"limit":"5"} (max 5). Segments use native Segment JSON; Google validates nested filter/segment semantics. Returns funnelTable and funnelVisualization with named rows, metadata and propertyQuota. No offset exists; possiblyTruncated flags subreports at the limit. Narrow the query then.
Inputs: steps (required), end_date (required), start_date (required), limit, +8 more. Returns: object
run_realtime_reportBRead-onlyIdempotent
Read realtime data; defaults to activeUsers over the last 30 minutes.
minutes_ago is inclusive (0–29 standard; 30–59 requires Analytics 360). Use realtime-specific dimensions/metrics such as country and activeUsers/eventCount. No offset exists in realtime; truncated=true means narrow dimensions/filters or raise limit.
Inputs: limit, account, metrics, order_bys, +5 more. Returns: object
run_reportARead-onlyIdempotent
Query GA4 (max 9 dimensions, 10 metrics, 10,000 rows per call).
Dates are inclusive: YYYY-MM-DD, today, yesterday, or NdaysAgo, in the property timezone. property_id is numeric or properties/123; omission uses GOOGLE_GA4_PROPERTY_ID. Filters use Google's FilterExpression JSON; e.g. {"filter":{"fieldName":"country","stringFilter":{"matchType":"EXACT","value":"Switzerland"}}}. order_bys uses Google OrderBy JSON, e.g. [{"metric":{"metricName":"sessions"},"desc":true}]. Use deterministic order_bys and nextOffset to page. Metrics are numeric strings, never zero-filled when absent. Keep metadata/quota when interpreting data quality and limits.
Inputs: metrics (required), end_date (required), start_date (required), limit, +9 more. Returns: object
search_change_historyARead-onlyIdempotent
Read configuration change history, requiring appropriate Editor/Administrator access.
ga_account_id is numeric or accounts/123 from list_properties; account is a login alias. property_id optionally limits the search; omission searches the account, ignoring the default property. Times are RFC3339, e.g. 2026-10-01T00:00:00Z. actions: CREATED/UPDATED/DELETED. resource_types uses Google's ChangeHistoryResourceType enum; actor_emails filters editors. Follow nextPageToken with identical filters even after an empty page. Secret values are redacted. Changes offer diagnostic context, not proof of the cause of traffic changes.
Inputs: ga_account_id (required), account, actions, page_size, +6 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Most tools map to clearly distinct GA4 surfaces (core reports, realtime, funnel, metadata, config, annotations, change history, access audit), and the descriptions actively differentiate them. The main residual overlap is connection_status vs health_check, which both inspect local setup without network access, and the convenience wrappers (get_summary/get_traffic_sources/get_top_pages/get_events) versus run_report, though their fixed outputs make the boundaries readable.
The dominant pattern is verb_noun (get_property, list_properties, run_report, run_realtime_report, search_change_history, list_property_annotations). Two tools break it with noun-only names (connection_status, health_check), and batch_run_reports versus run_report / run_funnel_report / run_access_report is slightly irregular but still clearly in the same family.
At 18 tools this is on the heavier side, but each covers a genuinely different GA4 API surface (Data core, realtime, alpha funnel, Admin config/annotations/change history, access audit, batch). Nothing looks like filler, though a couple of local-diagnostic tools are marginal.
The read surface is broad: core and realtime reporting, batching, funnels, metadata/compatibility, property config, annotations, change history, and access audit. Gaps exist for cohort/pivot queries and any write/management operations (audiences, key events, data streams, custom definitions), but the server is evidently scoped as a read/inspection tool where core workflows are covered.
Maintenance
Related MCP Connectors
Read-only Google Analytics 4 MCP server for AI assistants.
Read-only Search Console analytics, URL inspection, indexing diagnostics, and sitemaps.
Read-only MCP access to sessions, funnels, campaigns, errors, live visitors, and anomalies.
Hosted, read-only Google Analytics 4 MCP: reports, period comparisons, realtime, custom fields.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables querying Google Analytics 4 data through MCP tools for running reports, listing properties, getting real-time metrics, and exploring metadata.89 npmMIT
- AlicenseNot gradedqualityCmaintenanceRead-only access to Google Analytics 4 reporting data, including traffic overview, top pages, traffic sources, and conversion events, supporting custom report queries via MCP.MIT
- FlicenseNot gradedqualityDmaintenanceEnables read-only access to Google Analytics 4 and Google Search Console data, allowing users to run reports, query search analytics, and generate combined snapshots for reporting.-
- AlicenseAqualityBmaintenanceEnables MCP clients to query Google Analytics 4 reporting and configuration data through 27 read-only tools, including pivots, funnels, realtime reports, Admin API inspection, and diagnostics, with identifiers redacted by default.27Apache 2.0