Google Analytics MCP server for AI agents
Let Claude, ChatGPT or your own agent read Google Analytics: 3 typed functions through one MCP server. No Google Analytics API key needed.
- Functions
- 3
- Sign-in
- For account actions
- Works with
- MCP, HTTP, Node, Python
Connect
An MCP server for Google Analytics alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/analytics_googleOne MCP server for Google Analytics and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes. Functions that need a login use the person's own account: how sign-in works.
Functions
Open a function to see its arguments, what it returns and how to call it.
getOverviewReads a property's rendered overview: sessions, active users, and event count.Arguments
Name Type Required propertyIdstringGoogleAnalyticsProperty.propertyId; omitted = Analytics' selected property.No Returns
GoogleAnalyticsOverviewinterface GoogleAnalyticsOverview { propertyId: string | null; sessions: number | null; activeUsers: number | null; eventCount: number | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/analytics_google/getOverviewCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.analytics_google.getOverview({});import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.analytics_google.getOverview({}))curl -X POST https://api.bowmark.ai/v1/sites/analytics_google/getOverview \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.analytics_google.getOverview({});listPropertiesLists every Google Analytics property the signed-in caller can open, with its numeric property id.Arguments
None.
Returns
GoogleAnalyticsProperty[]interface GoogleAnalyticsProperty { propertyId: string; // Google Analytics' numeric property id name: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/analytics_google/listPropertiesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.analytics_google.listProperties();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.analytics_google.listProperties())curl -X POST https://api.bowmark.ai/v1/sites/analytics_google/listProperties \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.analytics_google.listProperties();listTrafficSourcesReads a property's rendered traffic-acquisition table: source, sessions, users, and engagement rate.Arguments
Name Type Required propertyIdstringGoogleAnalyticsProperty.propertyId; omitted = Analytics' selected property.No Returns
GoogleAnalyticsTrafficSource[]interface GoogleAnalyticsTrafficSource { source: string; sessions: number | null; users: number | null; engagementRate: number | null; // percent }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/analytics_google/listTrafficSourcesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.analytics_google.listTrafficSources({});import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.analytics_google.listTrafficSources({}))curl -X POST https://api.bowmark.ai/v1/sites/analytics_google/listTrafficSources \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.analytics_google.listTrafficSources({});
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/analytics_google/<function> - OpenAPI
/v1/sites/analytics_google/openapi.json