How to integrate Google Analytics MCP with Autogen

Connect Autogen to Google Analytics MCP. Show all google analytics accounts i manage, get detailed info for a specific account, and more using natural language, with authentication handled for you.

Google Analytics logoGoogle Analytics
Oauth2

Google Analytics tracks and reports website traffic, user behavior, and conversions. It helps marketers optimize performance and understand customer journeys.

82 Tools

Introduction

This guide walks you through connecting Google Analytics to AutoGen using the Composio tool router. By the end, you'll have a working Google Analytics agent that can run standard and realtime reports, build funnel and pivot reports, manage audiences, create custom dimensions and metrics, and review properties through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Google Analytics account through Composio's Google Analytics MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Google Analytics with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Google Analytics
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Google Analytics tools
  • Run a live chat loop where you ask the agent to perform Google Analytics operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Google Analytics MCP server, and what's possible with it?

The Google Analytics MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Google Analytics account. It provides structured and secure access to your analytics data, enabling your agent to analyze traffic, retrieve account info, list audiences, and build custom datasets on your behalf.

  • View and manage analytics accounts: Let your agent retrieve detailed information about specific Google Analytics accounts or list all accounts you have access to.
  • Audience insights and segmentation: Easily have your agent list all audiences associated with a GA4 property, helping you understand and segment your visitors.
  • Create custom expanded datasets: Direct your agent to combine key dimensions and metrics into tailored datasets for deeper analysis and reporting.
  • Efficient property and resource discovery: Have your agent confirm the existence of properties and fetch their details, streamlining your analytics management workflow.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Google Analytics account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Google Analytics via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Google Analytics connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Google Analytics session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["google_analytics"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Google Analytics tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Google Analytics assistant agent with MCP tools
    agent = AssistantAgent(
        name="google_analytics_assistant",
        description="An AI assistant that helps with Google Analytics operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Google Analytics tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Google Analytics related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Google Analytics tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Google Analytics and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Google Analytics session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["google_analytics"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Google Analytics assistant agent with MCP tools
        agent = AssistantAgent(
            name="google_analytics_assistant",
            description="An AI assistant that helps with Google Analytics operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Google Analytics related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Google Analytics through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Google Analytics, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Google Analytics action and event your agent gets out of the box.

Archive Custom Dimension

Tool to archive a CustomDimension on a property.

Batch Run Pivot Reports

Tool to return multiple pivot reports in a batch for a GA4 property.

Batch Run Reports

Runs multiple analytics data reports for one GA4 property in a single request.

Check Compatibility

Tool to list dimensions and metrics compatible with a GA4 report request.

Create Audience

Create an Analytics audience from explicit membership filter clauses.

Create Audience Export

Tool to create an audience export for Google Analytics.

Create Audience List

Tool to create an audience list for later retrieval by initiating a long-running asynchronous request.

Create Channel Group

Create a custom GA4 channel group with ordered traffic grouping rules.

Create Custom Dimension

Tool to create a CustomDimension for a Google Analytics property.

Create Custom Metric

Tool to create a custom metric in Google Analytics.

Create Data Stream

Create a web, Android, or iOS data stream under a GA4 property.

Create Event Create Rule

Create a rule that emits a destination event when source-event conditions match.

Create Expanded Data Set

Create an expanded data set for a Google Analytics 360 property using specified dimensions and metrics.

Create Key Event

Create a key event definition for a Google Analytics property.

Create Property

Create an ordinary GA4 property under an Analytics account.

Create Recurring Audience List

Tool to create a recurring audience list that automatically generates new audience lists daily based on the latest data.

Create Report Task

Tool to create a report task as a long-running asynchronous request for customized Google Analytics event data reports.

Create Rollup Property

Tool to create a roll-up property.

Delete Key Event

Permanently delete a deletable key event from a Google Analytics property.

Get Account

Tool to retrieve a single Account by its resource name.

Get Attribution Settings

Tool to retrieve attribution configuration for a Google Analytics property.

Get Audience

Tool to retrieve a single Audience configuration from a Google Analytics property.

Get Audience Export

Tool to get configuration metadata about a specific audience export.

Get Audience List

Tool to get configuration metadata about a specific audience list.

Get Custom Dimension

Tool to retrieve a single CustomDimension by its resource name.

Get Data Redaction Settings

Retrieve client-side data redaction settings for a GA4 web data stream.

Get Data Retention Settings

Tool to retrieve data retention configuration for a Google Analytics property.

Get Data Sharing Settings

Tool to retrieve data sharing configuration for a Google Analytics account.

Get Data Stream

Retrieve one Google Analytics data stream by its resource name.

Get Global Site Tag

Retrieve the immutable installation snippet for a GA4 web data stream.

Get Google Signals Settings

Tool to retrieve Google Signals configuration settings for a GA4 property.

Get Key Event

Retrieve a Key Event by its resource name.

Get Metadata

Tool to get metadata for dimensions, metrics, and comparisons for a GA4 property.

Get Property

Tool to retrieve a single GA4 Property by its resource name.

Get Property Quotas Snapshot

Tool to retrieve all property quotas organized by category (corePropertyQuota, funnelPropertyQuota, realtimePropertyQuota) for a given GA4 property.

Get Recurring Audience List

Tool to get configuration metadata about a specific recurring audience list.

Get Report Task

Tool to get report metadata about a specific report task.

List Access Bindings

List principals and roles granted on an Analytics account or property.

List Account Summaries

Tool to retrieve summaries of all Google Analytics accounts accessible by the caller.

List Accounts (v1beta)

List Google Analytics accounts accessible to the caller using the v1beta API.

List AdSense Links

Lists a page of AdSense links for a Google Analytics property.

List Audience Exports

Tool to list all audience exports for a property.

List Audience Lists

Tool to list all audience lists for a specified property to help find and reuse existing lists.

List Audiences

List audience configurations for a Google Analytics property; audiences created before 2020 may not be supported.

List BigQuery Links

Tool to list BigQuery Links on a property.

List Calculated Metrics

List Calculated Metrics

List Channel Groups

Tool to list ChannelGroups on a property.

List Conversion Events

Lists deprecated conversion event resources configured for a Google Analytics property.

List Custom Dimensions

List Custom Dimensions

List Custom Metrics

Tool to list CustomMetrics on a property.

List DataStreams

Tool to list DataStreams on a property.

List Display & Video 360 Advertiser Links

Tool to list Display & Video 360 advertiser links on a property.

List DisplayVideo360 Advertiser Link Proposals

Tool to list DisplayVideo360AdvertiserLinkProposals on a property.

List Event Create Rules

Tool to list EventCreateRules configured on a web data stream.

List Event Edit Rules

List event edit rules configured on a GA4 web data stream.

List Expanded Data Sets

Tool to list ExpandedDataSets on a property.

List Firebase Links

Tool to list FirebaseLinks on a property.

List Google Ads Links

Tool to list GoogleAdsLinks on a property.

List Key Events

List key event definitions for a Google Analytics property.

List Measurement Protocol Secrets

Tool to list MeasurementProtocolSecrets under a data stream.

List Property

Tool to list GA4 properties based on filter criteria.

List Recurring Audience Lists

List a page of recurring audience lists for a GA4 property, with a continuation token when more results are available.

List Reporting Data Annotations

List a page of Reporting Data Annotations for a specific GA4 property, optionally filtering the results.

List Report Tasks

List a page of report tasks for a Google Analytics property, including task definitions and execution status.

List Search Ads 360 Links

Tool to list all SearchAds360Links on a property.

List SKAdNetwork Conversion Value Schemas

Tool to list SKAdNetworkConversionValueSchema configurations for an iOS data stream.

List Subproperty Event Filters

List a page of subproperty event filters on a property, including filters that route events to subproperties.

List Subproperty Sync Configs

Tool to list SubpropertySyncConfig resources for managing subproperty synchronization configurations.

Provision Account Ticket

Tool to request a ticket for creating a Google Analytics account.

Query Audience Export

Tool to query a completed audience export.

Query Audience List

Tool to query an audience list.

Query Report Task

Tool to retrieve a report task's content.

Run Funnel Report

Tool to run a GA4 funnel report.

Run Pivot Report

Tool to run a customized pivot report of Google Analytics event data.

Run Realtime Report

Tool to run a customized realtime report of Google Analytics event data.

Run Report

Run a customized GA4 event-data report for a property using dimensions, metrics, filters and date ranges or a cohort specification.

Send Events

Send GA4 web-stream events using the Measurement Protocol and an API secret.

Delete Property

Move a Google Analytics property to the Trash Can and return its deletion state.

Update Data Retention Settings

Update selected data retention settings for a Google Analytics property.

Update Data Stream

Update a stream's display name, web default URI, or both.

Update Property

Tool to update an existing GA4 Property.

Validate Events

Validate Measurement Protocol events for a web stream before sending them to production, checking event structure and parameters.

FAQ

Frequently asked questions

Start with Google Analytics.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Google Analytics tool your agent needs.Free to start.

Start building