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.

Google Analytics MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Google Analytics
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Google Analytics through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Google Analytics "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Google Analytics?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Google Analytics MCP Server

Connect your Google Analytics 4 (GA4) account to any AI agent and take full control of web and app analytics through natural conversation.

Pydantic AI validates every Google Analytics tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Custom Reports — Run reports with any combination of metrics (activeUsers, screenPageViews, sessions, eventCount) and dimensions (city, country, deviceCategory, channel grouping)
Realtime Data — Monitor what's happening on your site right now with live user counts, events, and traffic sources from the last 30-60 minutes
Batch Reports — Execute multiple report configurations in a single API call for efficient dashboard loading
Metadata Discovery — List all available metrics and dimensions for your property, including custom definitions
Compatibility Checks — Validate metric/dimension combinations before running reports to avoid errors
Audience Exports — List and monitor audience export jobs for user segmentation and activation
User Activity — Retrieve event history for specific users for journey analysis and support investigations
Funnel Analysis — Visualize user progression through conversion steps and identify drop-off points

The Google Analytics MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Google Analytics to Pydantic AI via MCP

Follow these steps to integrate the Google Analytics MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Google Analytics with type-safe schemas

Why Use Pydantic AI with the Google Analytics MCP Server

Pydantic AI provides unique advantages when paired with Google Analytics through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Google Analytics integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Google Analytics connection logic from agent behavior for testable, maintainable code

Google Analytics + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Google Analytics MCP Server delivers measurable value.

Type-safe data pipelines: query Google Analytics with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Google Analytics tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Google Analytics and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Google Analytics responses and write comprehensive agent tests

Google Analytics MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Google Analytics to Pydantic AI via MCP:

batch_run_reports

Provide property_id and an array of report configurations. Each report can have different metrics, dimensions, and date ranges. This is efficient for dashboard loading or comparative analysis. The reports parameter should be a JSON array of report objects with metrics, dimensions, and dateRanges. Run multiple reports in a single API call

check_compatibility

Before running complex reports, use this to ensure compatibility between your chosen metrics and dimensions. This prevents errors and wasted API calls. Provide property_id and the metrics/dimensions you plan to use. Returns compatibility status and any conflicts that would prevent the report from running successfully. Check if metrics and dimensions can be combined in a report

get_audience_export

Audience exports allow you to extract user lists matching specific audience criteria. Use this to monitor the progress of audience extraction jobs. Provide property_id and the audience_export_id from list_audience_exports. Get status of a specific audience export

get_metadata

This includes both standard and custom metrics/dimensions with their descriptions, types, and compatibility information. Use this to discover what data is available before building reports. The propertyId is required and can be found in your GA4 admin settings. Get available metrics and dimensions for a GA4 property

get_property

Use the property_id obtained from list_properties to inspect property configuration. Get detailed information about a specific GA4 property

get_user_activity

This shows all interactions a user has had with your property, including pageviews, events, and conversions. Use this for user-level analysis, journey mapping, or support investigations. The userId must match the one sent with your tracking events. Get activity history for a specific user

list_accounts

This is the top-level container for properties. Each account can contain multiple properties. Use this to discover what accounts are available before drilling down into properties. List all Google Analytics accounts accessible to the user

list_audience_exports

Audience exports are used to extract user lists matching specific audience criteria for activation in other platforms. Shows status (CREATING, ACTIVE, FAILED) and configuration of each export job. List all audience export jobs for a property

list_properties

Properties represent individual websites, apps, or measurement streams. Each property has a unique ID needed for running reports. Use this to find the correct property_id for report queries. List all GA4 properties in an account

run_funnel_report

This helps identify where users drop off in conversion paths like checkout flows or signup processes. Provide property_id and a funnelSpec object defining the steps and breakdown settings. The funnelSpec should be a JSON object with steps array containing stepName, filterExpression, and optional breakdown settings. Run a funnel analysis report

run_realtime_report

Unlike standard reports, this shows what's happening on your site/app right now. Provide property_id and the metrics/dimensions you want to monitor in realtime. Common realtime metrics: activeUsers, eventCount, screenPageViews. Common realtime dimensions: city, country, deviceCategory, streamId. Get realtime analytics data (last 30-60 minutes)

run_report

You must provide the property_id, metrics (e.g., 'activeUsers', 'screenPageViews', 'eventCount'), and dimensions (e.g., 'city', 'pageTitle', 'sessionDefaultChannelGrouping'). Date ranges use YYYY-MM-DD format. Optional filter expression can narrow results. Common metrics: activeUsers, screenPageViews, sessions, eventCount, engagementRate, averageSessionDuration. Common dimensions: city, country, deviceCategory, sessionDefaultChannelGrouping, pageTitle, pagePath. Run a custom Google Analytics report

Example Prompts for Google Analytics in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Google Analytics immediately.

"Show me the number of active users and pageviews by country for the last 7 days for property 123456789."

"What's happening on the site right now? Show me realtime users by traffic source."

"Run a funnel analysis for our checkout flow: step 1 = viewed product, step 2 = added to cart, step 3 = started checkout, step 4 = completed purchase. Show me where users drop off."

Troubleshooting Google Analytics MCP Server with Pydantic AI

Common issues when connecting Google Analytics to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Google Analytics + Pydantic AI FAQ

Common questions about integrating Google Analytics MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Google Analytics MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.