AnalyticsFreeFirst-Party Ground TruthRequires GA4 OAuthActive in MCP

Get Website Analytics

get_website_analytics(domain: string, startDate: string, endDate: string, dimension?: enum)

Sessions/users/engagement from owned website analytics.

First-party Google Analytics 4 (GA4) traffic metrics: sessions, active users, and average engagement rate.

Input Parameters

4 arguments

Parameter	Type	Requirement	Default / Constraints	Description
`domain`	`string`	required	none	A tracked website's primary_domain (e.g. example.com).
`startDate`	`string`	required	ISO date format: YYYY-MM-DD	Start date for GA4 report.
`endDate`	`string`	required	ISO date format: YYYY-MM-DD	End date for GA4 report.
`dimension`	`enum`	optional	default: `date`date \| pagePath \| sessionSource	Break traffic metrics down by calendar date, landing page path, or session acquisition source.

Return Envelope (OFE / 1.0)

Open Fact Envelope

Every response adheres to the strict ofe/1.0 envelope schema, returning verified data, typed facts, entity references, and follow-up tool suggestions:

`data` Payload

First-party Google Analytics 4 (GA4) traffic metrics: sessions, active users, and average engagement rate.

`coverage` & Freshness

Reports returned count vs total items, observation timestamp as_of, and scope notes. Evaluated live per request.

`resources` (Dataset Exports)

If a query yields high row counts (e.g. >1,000 queries in Search Console), full unpaginated tables are persisted to R2 and linked as an mcpseo:// URI for follow-up retrieval via export_dataset.

`next_actions`

Provides suggested follow-up tool calls with pre-filled arguments so your AI agent can navigate from discovery to detailed inspection autonomously.

Emitted Facts & Entities

Knowledge Graph

Typed Facts

Facts emitted in the facts[] array with provenance receipts:

Fact Type	Claim Description	Emitted Data Fields
`analytics.traffic_summary`	Aggregated period totals for sessions, active users, and engagement rate.	`sessionsactive_usersavg_engagement_ratestart_dateend_date`
`analytics.traffic_by_dimension`	Row breakdown for selected dimension (date, page, or referral source).	`dimensiondimension_valuesessionsactive_usersengagement_rate`

Registered Entities

Entities registered in the entities[] array to establish subject relationships:

property

Connected GA4 property entity.

page

Landing page entities when dimension is 'pagePath'.

Request & Response Examples

Live MCP Payloads

Exact JSON schemas transmitted over Model Context Protocol (stdio or HTTP SSE transport):

1. Client Tool Invocationget_website_analytics request.json
{
  "tool": "get_website_analytics",
  "arguments": {
    "domain": "example.com",
    "startDate": "2026-09-01",
    "endDate": "2026-09-20",
    "dimension": "pagePath"
  }
}

2. Server Envelope Responseget_website_analytics response.json
{
  "schema_version": "ofe/1.0",
  "domain": "analytics",
  "data": {
    "domain": "example.com",
    "startDate": "2026-09-01",
    "endDate": "2026-09-20",
    "dimension": "pagePath",
    "totals": {
      "sessions": 48500,
      "activeUsers": 34200,
      "avgEngagementRate": 0.642
    }
  },
  "facts": [
    {
      "type": "analytics.traffic_summary",
      "subject": [
        "urn:property:ws_12345"
      ],
      "data": {
        "sessions": 48500,
        "active_users": 34200,
        "avg_engagement_rate": 0.642,
        "start_date": "2026-09-01",
        "end_date": "2026-09-20"
      },
      "provenance": {
        "source_class": "analytics_property",
        "method": "analyticsdata.properties.runReport",
        "confidence": 1,
        "observed_at": "2026-09-24T00:00:00Z",
        "cache_hit": false
      }
    },
    {
      "type": "analytics.traffic_by_dimension",
      "subject": [
        "urn:property:ws_12345",
        "urn:page:%2Fpricing"
      ],
      "data": {
        "dimension": "pagePath",
        "dimension_value": "/pricing",
        "sessions": 12400,
        "active_users": 9800,
        "engagement_rate": 0.781
      },
      "provenance": {
        "source_class": "analytics_property",
        "method": "analyticsdata.properties.runReport",
        "confidence": 1,
        "observed_at": "2026-09-24T00:00:00Z",
        "cache_hit": false
      }
    }
  ],
  "entities": [
    {
      "id": "urn:property:ws_12345",
      "kind": "property",
      "label": "Example Prod"
    },
    {
      "id": "urn:page:%2Fpricing",
      "kind": "page",
      "label": "/pricing"
    }
  ],
  "coverage": {
    "returned": 2,
    "total": 2,
    "as_of": "2026-09-20",
    "scope_note": null
  },
  "deltas": [],
  "resources": [],
  "next_actions": []
}

LLM Agent Workflow

Claude & Cursor Integration

Step 1

Prompt Trigger

"How engaged are visitors on /pricing compared to the rest of the site in GA4?"

Step 2

Agent Decision & Reasoning

The agent pulls first-party GA4 engagement metrics to correlate search impression traffic with actual conversion and on-page dwell times.

Step 3

Recommended Follow-up Tools

get_search_performance →

Provenance Guarantees & Error Handling

Reliability

Source Classanalytics_property

Inspection Methodanalyticsdata.properties.runReport

OFE Calibration Score1.00 (OFE 1.0 scale)

Cache DurationNone (Live)

Every fact emitted by Vouched includes source_class, method, observed_at ISO timestamp, and a published confidence score. LLM agents can inspect these citations to distinguish first-party verified facts (e.g. Search Console) from modeled competitor estimates.

Billing & API Keys

Free on every plan: it reads your own Google data, so there's no per-call cost. Works the same when self-hosted.

Connection Required: Requires connecting your Google Analytics (GA4) property via OAuth. Until it's connected, calls return a connection_required error saying where to connect it (Settings in the dashboard).

Error Conditions

ConnectionRequiredError: no GA4 property configured for domain. Add connection via /dashboard/connections.

Self-host on GitHub (MIT)Try on Cloud plan