Google Analytics MCP. Run complex reports on user behavior paths.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Google Analytics connects your AI client directly to GA4 data streams. Run reports, analyze user funnels, and check real-time site activity using natural conversation.
You query custom metrics like active users or screen page views across all properties without touching the web interface.
What your AI agents can do
Batch run reports
Runs multiple, different reports in a single API call for efficient dashboard loading.
Check compatibility
Verifies if your chosen metrics and dimensions can be combined successfully in a report.
Get audience export
Monitors the status of an audience export job, allowing you to track user list generation progress.
Execute detailed analytics reports by specifying metrics (e.g., sessions) and dimensions (e.g., country).
Get immediate data on current site traffic, including live user counts and top sources for the last hour.
Map out conversion paths to identify specific steps in a process where users drop off (e.g., checkout flow).
List all available properties and accounts, ensuring you run reports against the correct data source.
Validate that your chosen metrics and dimensions work together before running a report to avoid API errors.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Google Analytics: 12 Tools for Data Reporting & Export
These tools give your AI client granular access to the Google Analytics API. You can list properties, check data fields, and run specialized reports on user behavior.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Google Analytics on Vinkius019d75a7batch run reports
Runs multiple, different reports in a single API call for efficient dashboard loading.
019d75a7check compatibility
Verifies if your chosen metrics and dimensions can be combined successfully in a report.
019d75a7get audience export
Monitors the status of an audience export job, allowing you to track user list generation progress.
019d75a7get metadata
Lists all available metrics and dimensions for your property so you know what data is trackable.
019d75a7get property
Retrieves detailed configuration information about a specific GA4 property.
019d75a7get user activity
Gets the full history of interactions (pageviews, events) for one specific user ID.
019d75a7list accounts
Lists all Google Analytics accounts available to you, which contain multiple properties.
019d75a7list audience exports
Shows the current status (like CREATING or FAILED) for every audience export job run on a property.
019d75a7list properties
Lists all individual websites or apps (properties) within an account, providing their necessary IDs.
019d75a7run funnel report
Analyzes the steps users take through a process to show where they abandon the flow.
019d75a7run realtime report
Displays live analytics data for traffic, events, and users over the last 30-60 minutes.
019d75a7run report
Runs a standard custom report using specific metrics, dimensions, and date ranges.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Google Analytics, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Google Analytics 4. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Sifting through GA4 dashboards takes forever.
Today, if you want to compare user activity across multiple dimensions—say, seeing how 'activeUsers' and 'sessions' differ between 'mobile' and 'desktop' users in the last quarter—you have to navigate the entire GA4 web interface. You click into the correct report, adjust date ranges, select metrics, then filter by device category. It's a multi-step process that requires constant context switching.
With this MCP server, you just tell your agent: 'Give me active users and sessions, broken down by device category for Q2.' The AI executes the `run_report` tool immediately. You get structured data in seconds. No dashboard navigation required.
Run a funnel analysis using `run_funnel_report`. Get actionable drop-off points.
Without the dedicated function, mapping out complex conversion paths is difficult. You might have to run multiple separate reports—one for 'viewed product,' another for 'added to cart'—and then manually compare and calculate the drop-off rates yourself in a spreadsheet. It's tedious, error-prone work.
The `run_funnel_report` tool takes all those steps and calculations off your plate. You define the funnel steps once, run the report, and get a single output that shows exactly where the biggest percentage drop-off occurs.
What you can do with this MCP connector
Your AI client connects straight into your Google Analytics 4 data streams. You run reports, check user funnels, and see real-time site activity just by talking to it. It lets you query specific metrics—like active users or screen page views—across all your properties without ever touching the GA web interface.
To get started, you'll first need to know what data you're dealing with. You can use list_accounts to see every Google Analytics account associated with your login. Then, running list_properties gives you a list of all individual websites or apps—the properties—within those accounts, giving you the IDs you need to target.
If you want specific configuration details for one property, call get_property. When you're ready to see what data fields are even available, run get_metadata; that lists every single metric and dimension your property tracks, including custom ones.
When it comes time to build reports, you don't have to build 'em manually. You can use run_report for a standard custom report by specifying metrics, dimensions, and the date range. If you need several different reports loaded up fast, batch_run_reports runs multiple distinct reports in one API call. Before running any big query, though, check your work with check_compatibility; this verifies that the specific metrics and dimensions you picked can actually be combined successfully into a single report.
You also get immediate data on current site traffic by using run_realtime_report, which displays live analytics for users, events, and traffic sources over the last 30 to 60 minutes.
For deep user analysis, you've got two main options. To map out conversion paths and see exactly where people drop off—like during a checkout flow—you run run_funnel_report. If you want to track one specific person's journey, you can use get_user_activity to get the full history of interactions (pageviews, events) for just that user ID.
You also monitor audience list generation using export tools; call list_audience_exports to see the current status—whether it’s CREATING or FAILED—for every audience export job run on a property, and use get_audience_export to track the progress of one specific job.
019d75a7-f4bf-73a3-9f8f-8e9e57bfb95c 
How Google Analytics MCP Works
- 1 Subscribe to the server and input your Google Analytics API key from Google Cloud Console.
- 2 Ask your AI agent to perform an action (e.g., 'Run a funnel report for checkout').
- 3 The agent calls the necessary tool (
run_funnel_report) and returns structured data containing the calculated metrics.
The bottom line is, you treat the GA4 API like a function call within your conversation flow.
Who Is Google Analytics MCP For?
Product Managers who need to know why users are dropping off; Data Analysts stuck clicking through dashboards for basic metrics; and Marketing Leads who want to run ad performance reports instantly, without opening the Google console.
Runs batch_run_reports or list_properties to pull large sets of data for BI tools or comparative analysis.
Uses run_funnel_report to map conversion steps and identifies which stage causes the highest user drop-off rate.
Queries realtime data via run_realtime_report to check immediate campaign performance or traffic spikes by country.
What Changes When You Connect
- Funnel Analysis: Use
run_funnel_reportto see exactly where users drop off during checkout or sign-up. This pinpoints conversion roadblocks immediately. - Realtime Visibility: Ask for a report using
run_realtime_reportand get live counts of active users by country, without waiting for the next day's data sync. - Scope Check: Need to know which reports you can run? Use
get_metadatafirst. It lists every trackable metric and dimension in your property. - Efficiency Boost: Don't call the API multiple times. Group complex requests into one go using
batch_run_reportsfor faster dashboard loading. - Deep User Dive: Investigate a single problematic customer by calling
get_user_activity, retrieving their entire journey history by user ID.
Real-World Use Cases
Investigating a Traffic Dip
A support team member notices a dip in traffic from 'Organic Search'. Instead of manually building an ad-hoc report, they ask their agent to run run_realtime_report for the last 60 minutes. The agent provides immediate data showing the drop is isolated to one specific city, allowing the team to check local campaigns.
Optimizing Signups
A Product Manager suspects users are leaving during checkout. They use run_funnel_report on the signup flow. The report shows a massive drop-off between 'Started Checkout' and 'Completed Purchase,' confirming they need to fix payment options.
Audience Segmentation
Marketing wants a list of users who viewed Product X but didn't buy in the last 30 days. They use list_audience_exports and then trigger get_audience_export to get the ID, automating their user segment creation.
Pre-Flight Check
A Data Analyst needs a complex report combining 'eventCount' and 'deviceCategory.' Before running the main query, they use check_compatibility. The tool flags that these two metrics cannot be combined in one view, saving hours of debugging.
The Tradeoffs
Running Reports Blindly
Just running the basic run_report with vague parameters and hoping it works. You end up hitting API limits or getting ambiguous errors because you didn't check field compatibility.
→
Always start by calling get_metadata to understand available data fields. If your planned metrics/dimensions seem incompatible, use check_compatibility before running any report.
Querying without Scope
Trying to run a complex query when you aren't sure which website ID (property_id) the data belongs to. The call fails because the server doesn't know where to look.
→
First, use list_accounts and then list_properties to identify the exact property IDs. Use one of these IDs in every report query.
Forgetting User Context
Asking for general conversion data when you actually need to investigate a specific customer's problem. The result is useless because it lacks personal context.
→
If the goal is support or deep troubleshooting, use get_user_activity and provide the exact userId. This gives the full history of that one user.
When It Fits, When It Doesn't
Use this server if your core need is measuring web and app behavior (conversions, traffic sources, funnels). You're diagnosing how users moved through a site.
Don't use it if you need internal system logs, database query results, or financial transaction records. For those, you need a different logging endpoint. If you just want to know what reports could be run, start with get_metadata. If you have multiple reports that share the same parameters, use batch_run_reports instead of running them one by one.
Common Questions About Google Analytics MCP
How do I find out what metrics are available using `get_metadata`? +
get_metadata lists all available standard and custom metrics/dimensions for your property. This is the first tool you should run if you don't know the exact field names required for a report.
What is the difference between `run_report` and `batch_run_reports`? +
run_report executes one single, custom query. Use batch_run_reports when you need to run several different report configurations (different metrics/dimensions) in a single API call for efficiency.
Can I see what a specific user did with `get_user_activity`? +
Yes, but you must provide the correct userId. This tool pulls every recorded event, pageview, and conversion associated only with that unique ID.
How do I check if my metrics will work together? Should I use `check_compatibility`? +
Yes, always run check_compatibility. It verifies your chosen metrics and dimensions before you waste time running a report that will fail due to data conflict.
I want to see what is happening on my site right now. Which tool should I use? +
Use run_realtime_report. This function bypasses standard historical reporting and provides live metrics for the last 30-60 minutes, perfect for checking immediate traffic spikes.
How do I find all available properties in an account before running a report with `list_properties`? +
You use list_properties to retrieve a list of property IDs. This is crucial because every report, whether custom or real-time, requires the specific property ID as its primary input.
I just ran an audience export job; how can I check its current status using `get_audience_export`? +
The get_audience_export tool confirms the progress of your data extraction. It returns the current state—whether the job is CREATING, ACTIVE, or FAILED—so you know when to expect the user list.
If my organization has multiple divisions, how do I see all top-level containers using `list_accounts`? +
list_accounts shows every Google Analytics account associated with your credentials. This gives you a high-level view of which business units or properties groups are available to query.
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.
Multi-server workflows that include Google Analytics MCP
Audit Agency Websites Using MCP Servers
Your agency manages 15 client Webflow sites but nobody checks if last month's landing page update actually improved conversions , the designer shipped it, the PM marked it done, and the page sits there with a 0.4% conversion rate that nobody measures
MCP Recipe for Agency SEO Dashboards
Your SEO manager manually exports Google Analytics data for 8 clients every Monday morning , and by the time the last client report is done, the first client's data is already a week old
MCP Recipe for Email Campaign Attribution
Your email campaign got a 24% open rate and 3.8% click rate , which tells the client nothing about how many people actually visited the site, filled out a form, or became a paying customer from that email
MCP Recipe to Track Social Media ROI
Your social media manager posts 40 times per week across 8 client accounts but has no idea which posts drive website traffic , they report on likes and shares while the client asks 'but did anyone actually visit our site?'
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.