mcp server
Google Analytics (unofficial)
Connect Google Analytics to ChatGPT. Query GA4 data in plain English and get instant insights.
Description as published by the maintainer. Source
- version 1.0.0
- slowing
- analytics
slowing — Registry entry last updated 2026-02-07. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
What this server can do
5 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
marketing_get_catalog(source)- Use this when the user wants to discover the canonical marketing reporting graph, available sources, supported metrics, supported dimensions, or which connectors are live today. Each source also reports a `passthrough` field describing whether native fields beyond the curated list are accepted (GA4 accepts any native dimension/metric; Search Console accepts any native dimension; Bing is limited to the curated fields). Do not use this for GA4 account discovery or data retrieval.
marketing_get_funnel(app, type, limit, funnel, property, surfaceId, dateRanges, propertyId, appStreamId, bingSiteUrl, ga4PropertyId, funnelBreakdown, funnelNextAction, returnPropertyQuota, searchConsoleSiteUrl, funnelVisualizationType)- Use for ordered conversion-step analysis: GA4 ordered_steps step funnels (e.g. session_start → add_to_cart → purchase) and cross-source holistic_bundle landing-page funnels joining GA4, Google Search Console, and Bing Webmaster. Covers funnel drop-off between steps (e.g. from landing on the site to adding to cart to purchasing), conversion paths, and acquisition-to-conversion context. Pass one date range for a single window or two date ranges for period-over-period comparison. Required: type, dateRanges.
marketing_get_report(app, site, limit, offset, source, maxRows, metrics, siteUrl, sources, orderBys, pageSize, property, surfaceId, dateRanges, dimensions, metricMode, propertyId, sourceMode, appStreamId, significance, keepEmptyRows, metricFilters, returnAllRows, sourceOptions, dimensionFilters, metricFilterExpression, dimensionFilterExpression)- Primary reporting tool for a given GA4 property or site. Use for totals, trends, and breakdowns by dimension across GA4 website traffic and app analytics, Google Search Console site traffic, and Bing Webmaster — including last-30-days summaries, revenue, leads, sessions, users, engagement/time-on-page (average_session_duration, user_engagement_duration), and period-over-period comparisons. Drill deep: GA4 supports up to 9 grouped dimensions (date/hour, geo, device/browser/OS, source/medium/channel, landing_page/page_path, etc.). Defaults to all mapped connected sources merged into one standardized view, aligned on the shared grain (typically landing_page) so a page row blends GA4 sessions+engagement with Search Console/Bing clicks/impressions/CTR/position; per-source detail (e.g. full query lists) stays in sourceSections. Note GA4 has no `query` dimension and Search Console/Bing have no sessions/engagement, so those cannot share one row — query is a Search Console/Bing breakdown. Narrow with sources or sourceMode='single'. Any GA4 dimension/metric name not in the catalog is passed through to the GA4 API automatically; metricMode='source_native' forces a pure GA4-native report. Pass one date range for a single window or two date ranges for period-over-period comparison. Required: dateRanges, metrics.
marketing_get_sources(sources, surfaceId)- Lists connected and missing GA4, Google Analytics properties, property IDs, web streams, app streams, measurement IDs, Firebase app IDs, Google Search Console sites, Bing Webmaster sites, and current analysis surface mappings. Use this before reporting when property/site selectors are unknown.
marketing_manage_surface(name, action, selectors, surfaceId, mainDomain, selectorSets)- Gets or updates persisted selectors for a website/app analysis surface. Use action='get' to inspect mappings and action='update' to persist GA4, Search Console, or Bing Webmaster selectors. Required: action.
Last successful function declaration observed on . Source: https://api.safe-mcp.com/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://api.safe-mcp.com/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 1.0.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-02-07 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-02-07 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 5 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | api.safe-mcp.com | |
| mcp endpoint status | ok | The server listed 5 functions when asked. | as of probe | api.safe-mcp.com |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json