# Google Analytics MCP for AI Agents AI Agent Connect > Google Analytics MCP lets you query GA4 data through natural conversation. Run custom reports, check realtime traffic, analyze conversion funnels, and manage audience exports directly from your AI agent. It removes the friction of navigating the dashboard and turns complex data into clear answers. ## Overview - **Category:** industry-titans - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_v8thcnqdwIs5ecz18LHuEc3p1uB6nf8I9CCTGT2t/ai-agent-connect - **Tags:** web-analytics, user-behavior, conversion-tracking, real-time-data, funnel-analysis, audience-insights ## Description Stop hunting through nested menus and filters in the Google Analytics dashboard just to find out where your traffic is coming from. This Connector lets you treat your data like a conversation. Instead of manually building reports for every single request, you can just ask your agent to pull the numbers. It handles the heavy lifting of fetching active user counts, session data, and geographic breakdowns across your properties. You can check what's happening on your site right now or look back at specific conversion paths to see exactly where people are dropping off. It's designed to turn your AI into a dedicated analyst that knows your data inside and out. By connecting this through the Vinkius catalog, you get a direct line to your GA4 metrics. You can pull custom reports with specific dimensions like device category or channel grouping, and even monitor the status of your audience export jobs. It's about moving from how do I get this data to what does this data mean for my next move. You get the answers you need in plain text, ready for you to use in your next meeting, product sprint, or marketing strategy session. You don't have to worry about the technicalities of the API or the friction of the dashboard interface anymore. ## Tools ### batch_run_reports Run multiple report configurations in one call to load several data points at once. This is great for loading large dashboards quickly. ### check_compatibility Verify if your chosen metrics and dimensions can work together before you run a report. This helps you avoid wasted API calls and errors. ### get_audience_export Check the current status of a specific audience extraction job. Use this to see if your user lists are ready for activation. ### get_metadata See every metric and dimension available for your specific GA4 property. This helps you discover what data you can actually query. ### list_accounts See all the Google Analytics accounts you have access to. Use this to find the right account before drilling down into properties. ### get_property View the full configuration details for a specific GA4 property. This is useful for inspecting your measurement stream settings. ### get_user_activity Fetch the interaction history for a specific user ID to map out their journey. This is perfect for support investigations and user research. ### list_audience_exports View a list of all your current audience export jobs and their statuses. This helps you manage large-scale user segment extractions. ### list_properties Find the unique property IDs for all your websites and apps. You need these IDs to run any specific reports or queries. ### run_funnel_report Identify exactly where users drop off in a multi-step conversion path. This helps you find friction in your checkout or signup flows. ### run_realtime_report Get a snapshot of what's happening on your site over the last 30 to 60 minutes. See live user counts and current traffic sources. ### run_report Execute a custom report using your choice of metrics, dimensions, and date ranges. This is the primary way to query your GA4 data. ## Prompt Examples **Prompt:** ``` How many users from the UK visited our site in the last 7 days? ``` **Response:** ``` I've run the report for the last 7 days. Here are the top countries by active users: * United States: 45,230 active users, 189,450 pageviews * United Kingdom: 12,890 active users, 52,340 pageviews * Germany: 8,560 active users, 34,120 pageviews * Brazil: 6,780 active users, 28,900 pageviews * India: 5,420 active users, 21,560 pageviews Total: 156,420 active users across 645,890 pageviews. Would you like a breakdown by device category or traffic source? ``` **Prompt:** ``` Show me the conversion funnel for our new signup flow. ``` **Response:** ``` I've analyzed your signup funnel. Here is the conversion flow: 1. **Viewed Signup Page** — 12,450 users entered 2. **Started Registration** — 4,980 users (40.0% conversion from step 1) 3. **Completed Registration** — 2,340 users (47.0% conversion from step 2) **Overall funnel conversion rate: 18.5%** (2,340 out of 12,450) **Biggest drop-off**: Between Viewed Signup Page and Started Registration. 60% of users leave here. ``` **Prompt:** ``` What's happening on the site right now? ``` **Response:** ``` Realtime data (last 30 minutes): * **Active Users**: 847 right now * **Top Traffic Sources**: Organic Search (412), Direct (198), Social (124) * **Top Pages**: Homepage (234), Product Page (156), Checkout (89) Engagement rate is 68% with an average session duration of 2m 34s. ``` ## Capabilities ### Run custom reports Pull specific data points using any combination of metrics and dimensions. ### Monitor realtime traffic See what's happening on your site right now with live user counts and events. ### Analyze conversion funnels Identify exactly where users drop off in your checkout or signup flows. ### Pull user activity history Retrieve the specific interaction history for a single user ID. ### Check metric compatibility Verify if your chosen metrics and dimensions can work together before running a query. ### Monitor audience exports Track the status of your user list extraction jobs. ### Discover property metadata See all available metrics and dimensions for your specific GA4 property. ## Use Cases ### Finding traffic sources for a new launch A marketing manager asks for a breakdown of traffic by channel and country for the last 7 days. The agent uses run_report to pull the numbers instantly. ### Identifying checkout friction A product lead wants to see why people aren't finishing their purchases. They ask for a funnel report on the checkout flow to find the highest drop-off point. ### Troubleshooting a specific user issue A support agent uses get_user_activity to see the pages a frustrated customer visited before opening a ticket to provide better context. ### Validating data for a custom dashboard A data analyst uses get_metadata to see which dimensions are available for their region so they can build an accurate report without errors. ## Benefits - Stop manual dashboard navigation by using run_report to get specific data points instantly without clicking through menus. - Identify friction points in your checkout flow using run_funnel_report to see exactly where users quit the process. - Monitor live traffic spikes with run_realtime_report to see what's happening on your site right now. - Avoid API errors by using check_compatibility to ensure your metric and dimension choices are valid before you query. - Save time on data gathering by using batch_run_reports to pull multiple datasets in a single request. - Deepen user research by using get_user_activity to see the specific journeys of your customers and find where they get lost. ## How It Works The bottom line is you get instant access to GA4 data without ever touching a dashboard. 1. Subscribe to this Connector and provide your Google Cloud Console API key. 2. Connect your GA4 property via your preferred AI client. 3. Ask questions about your traffic, funnels, or user behavior. ## Frequently Asked Questions **Can I use Google Analytics MCP to see real-time traffic?** Yes, you can see what's happening on your site right now, including live user counts and top pages from the last 30 to 60 minutes. **Does Google Analytics MCP support custom reports?** It does. You can ask for any combination of metrics like sessions or events with dimensions like city, device category, or channel grouping. **How do I see where people drop off in my checkout?** You can ask the agent to run a funnel report. It will break down each step of your flow and show you the exact conversion rate between them. **Can I use Google Analytics MCP to look up specific user journeys?** Yes, if you have a user ID, you can pull their activity history to see every pageview and event they triggered. **Can I check if my report will work before I run it?** You can use the compatibility check to see if your chosen metrics and dimensions are allowed to be used together. **Does Google Analytics MCP work for both web and apps?** Yes, it connects to your GA4 property, which covers both your website and mobile app measurement streams. **How do I get a Google Analytics API key and what type of credentials do I need?** You need an API Key from Google Cloud Console. Go to **console.cloud.google.com** → Select or create a project → Enable the **Google Analytics Data API v1** → Navigate to **APIs & Services > Credentials** → Click **Create Credentials > API Key**. Copy the key (starts with `AIzaSy...`). Then, in Google Analytics Admin, add the service account email with Viewer or Analyst role to your GA4 property. Paste the API key below. **What metrics and dimensions are available in GA4 and how do I find them?** Use the `get_metadata` tool with your property_id to list all available metrics and dimensions. Common metrics include: `activeUsers`, `screenPageViews`, `sessions`, `eventCount`, `engagementRate`, `averageSessionDuration`, `conversions`. Common dimensions include: `city`, `country`, `deviceCategory`, `sessionDefaultChannelGrouping`, `pageTitle`, `pagePath`, `streamName`. The metadata response shows descriptions, types, and whether each field is a metric or dimension. **Can I get realtime data and how far back does it go?** Yes! Use the `run_realtime_report` tool to get data from the last 30-60 minutes. Realtime reports show active users, events, and traffic sources as they happen on your site. This is useful for monitoring campaign launches, tracking live events, or checking if tracking is working correctly. Unlike standard reports which can take 24-48 hours to process, realtime data is available within minutes. **How do I analyze funnel conversion rates and identify drop-off points?** Use the `run_funnel_report` tool with a funnel_spec JSON object defining your conversion steps. Each step includes a stepName, filterExpression (e.g., eventName equals 'page_view'), and optional breakdown settings. The response shows how many users entered each step, how many completed it, and where the biggest drop-offs occurred. This helps identify friction points in checkout flows, signup processes, or any multi-step user journey.