How to Use the Google Analytics 4 MCP in Google ADK

Q: Can I join Google Analytics 4 data with BigQuery tables using Google ADK?

Yes. The Google ADK can call gettrafficsources to retrieve web traffic and then pass that JSON payload directly to a BigQuery tool in the same agent workflow. This lets your agent run SQL joins on live GA4 metrics and historical warehouse data.

Q: How do I configure Google Analytics 4 tools in a Google ADK agent?

Instantiate McpToolset with the Vinkius HTTP URL and pass it to your LlmAgent tools array. You can use the optional toolnames filter to only expose specific analytics tools like getpageviews.

Q: Does Google ADK support real-time Google Analytics 4 reporting?

Yes, the agent can call runrealtimereport to get active user counts from the last 30 minutes. This is ideal for Gemini-powered monitoring agents that need to flag immediate traffic anomalies.

Feed live GA4 data directly into Gemini models using the Google ADK MCP Server to combine analytics with enterprise data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Analytics 4 MCP to Google ADK

Create your Vinkius account to connect Google Analytics 4 to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Google Analytics 4 with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyzing deep historical trends with Google ADK

`run_report` extracts massive slices of historical event data directly into the Google ADK long-context window using this MCP server. Gemini models easily digest thousands of rows of page views and traffic metrics in a single prompt, finding subtle correlations that shorter-context models miss. This integration allows your agent to compare year-over-year performance without aggressive data aggregation. The server handles the heavy lifting of pulling the raw numbers, leaving the analysis to your enterprise LLM.

Mapping acquisition paths in Google ADK

`get_traffic_sources` retrieves user acquisition channels to map exactly where your high-value converting traffic originates. The Google ADK passes this structured data directly to your BigQuery pipelines, letting you join web traffic with offline sales records. Your agent uses these combined datasets to calculate true customer acquisition costs. By querying the MCP server, the agent obtains clean, standardized channel groupings without manual CSV exports.

Verifying GA4 tracking setups via Google ADK

`check_compatibility` verifies that your selected dimensions and metrics can be queried together without triggering API errors. The Google ADK runs this check before executing complex pivot tables, saving API quota and preventing runtime failures. If a marketing manager asks the agent for an incompatible combination, the tool flags the issue immediately. The agent then suggests alternative fields using data retrieved from `get_metadata`.

Setup guide

Set up Google Analytics 4 MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Google Analytics 4 tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Google Analytics 4_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Google Analytics 4 tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Google Analytics 4 now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Google Analytics 4 MCP in Google ADK

Yes. The Google ADK can call `get_traffic_sources` to retrieve web traffic and then pass that JSON payload directly to a BigQuery tool in the same agent workflow. This lets your agent run SQL joins on live GA4 metrics and historical warehouse data.

Instantiate `McpToolset` with the Vinkius HTTP URL and pass it to your `LlmAgent` tools array. You can use the optional tool_names filter to only expose specific analytics tools like `get_page_views`.

Yes, the agent can call `run_realtime_report` to get active user counts from the last 30 minutes. This is ideal for Gemini-powered monitoring agents that need to flag immediate traffic anomalies.

Gemini's 1M+ token context window in the Google ADK easily accommodates large outputs from `run_pivot_report`. The agent processes the entire multi-dimensional dataset in a single turn without needing chunking strategies.

Your GA4 service account JSON and property IDs are stored securely in the Vinkius V8 Isolate Sandbox. The MCP server operates under a zero-trust model, ensuring your analytics data is never cached or exposed to external networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript