# How to integrate Google Analytics MCP with LlamaIndex

```json
{
  "title": "How to integrate Google Analytics MCP with LlamaIndex",
  "toolkit": "Google Analytics",
  "toolkit_slug": "google_analytics",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/google_analytics/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/google_analytics/framework/llama-index.md",
  "updated_at": "2026-05-12T10:13:36.303Z"
}
```

## Introduction

This guide walks you through connecting Google Analytics to LlamaIndex using the Composio tool router. By the end, you'll have a working Google Analytics agent that can show all google analytics accounts i manage, get detailed info for a specific account, list audiences for your ga4 property through natural language commands.
This guide will help you understand how to give your LlamaIndex 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.

## Also integrate Google Analytics with

- [ChatGPT](https://composio.dev/toolkits/google_analytics/framework/chatgpt)
- [Antigravity](https://composio.dev/toolkits/google_analytics/framework/antigravity)
- [OpenAI Agents SDK](https://composio.dev/toolkits/google_analytics/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/google_analytics/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/google_analytics/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/google_analytics/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/google_analytics/framework/codex)
- [Cursor](https://composio.dev/toolkits/google_analytics/framework/cursor)
- [VS Code](https://composio.dev/toolkits/google_analytics/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/google_analytics/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/google_analytics/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/google_analytics/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/google_analytics/framework/cli)
- [Google ADK](https://composio.dev/toolkits/google_analytics/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/google_analytics/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/google_analytics/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/google_analytics/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/google_analytics/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for Google Analytics
- Connect LlamaIndex to the Google Analytics MCP server
- Build a Google Analytics-powered agent using LlamaIndex
- Interact with Google Analytics through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built for async/await patterns

## 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.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `GOOGLE_ANALYTICS_ARCHIVE_CUSTOM_DIMENSION` | Archive Custom Dimension | Tool to archive a CustomDimension on a property. Use when you need to remove a custom dimension from active use without permanently deleting it. Archived dimensions cannot be used in new reports. |
| `GOOGLE_ANALYTICS_BATCH_RUN_PIVOT_REPORTS` | Batch Run Pivot Reports | Tool to return multiple pivot reports in a batch for a GA4 property. Use when you need to fetch multiple pivot table reports with multi-dimensional analysis in a single request. |
| `GOOGLE_ANALYTICS_BATCH_RUN_REPORTS` | Batch Run Reports | Tool to return multiple analytics data reports in a batch. Use when you need to fetch multiple reports for one GA4 property in a single request. |
| `GOOGLE_ANALYTICS_CHECK_COMPATIBILITY` | Check Compatibility | Tool to list dimensions and metrics compatible with a GA4 report request. Use when you need to validate compatibility of chosen dimensions or metrics before running a report. |
| `GOOGLE_ANALYTICS_CREATE_AUDIENCE_EXPORT` | Create Audience Export | Tool to create an audience export for Google Analytics. Use when you need to export a snapshot of users in an audience at a specific point in time. This initiates a long-running asynchronous request that returns an operation resource name immediately. The export begins in CREATING state with rowCount=0; the operation must complete before export data is accessible for querying. |
| `GOOGLE_ANALYTICS_CREATE_AUDIENCE_LIST` | Create Audience List | Tool to create an audience list for later retrieval by initiating a long-running asynchronous request. Use when you need to create a snapshot of users currently in an audience. The method returns quickly with an Operation resource while processing occurs in the background. |
| `GOOGLE_ANALYTICS_CREATE_CUSTOM_DIMENSION` | Create Custom Dimension | Tool to create a CustomDimension for a Google Analytics property. Use when you need to add a new custom dimension to track specific user properties, event parameters, or eCommerce item parameters. |
| `GOOGLE_ANALYTICS_CREATE_CUSTOM_METRIC` | Create Custom Metric | Tool to create a custom metric in Google Analytics. Use when you need to define a new custom metric for tracking specific event parameters. |
| `GOOGLE_ANALYTICS_CREATE_EXPANDED_DATA_SET` | Create Expanded Data Set | Tool to create an expanded data set for a property. Use when you need to combine specific dimensions and metrics into a custom dataset after property creation. |
| `GOOGLE_ANALYTICS_CREATE_RECURRING_AUDIENCE_LIST` | Create Recurring Audience List | Tool to create a recurring audience list that automatically generates new audience lists daily based on the latest data. Use when you need to automate audience list creation and reduce quota token consumption. |
| `GOOGLE_ANALYTICS_CREATE_REPORT_TASK` | Create Report Task | Tool to create a report task as a long-running asynchronous request for customized Google Analytics event data reports. Use when you need to generate large or complex reports that process asynchronously. |
| `GOOGLE_ANALYTICS_CREATE_ROLLUP_PROPERTY` | Create Rollup Property | Tool to create a roll-up property. Use when consolidating multiple GA4 properties into one aggregated view. |
| `GOOGLE_ANALYTICS_GET_ACCOUNT` | Get Account | Tool to retrieve a single Account by its resource name. Use when you need detailed account info after confirming the account resource name (e.g., accounts/100). |
| `GOOGLE_ANALYTICS_GET_ATTRIBUTION_SETTINGS` | Get Attribution Settings | Tool to retrieve attribution configuration for a Google Analytics property. Use when you need to check attribution models, lookback windows, and conversion export settings. |
| `GOOGLE_ANALYTICS_GET_AUDIENCE` | Get Audience | Tool to retrieve a single Audience configuration from a Google Analytics property. Use when you need detailed audience information including membership criteria and filter clauses. |
| `GOOGLE_ANALYTICS_GET_AUDIENCE_EXPORT` | Get Audience Export | Tool to get configuration metadata about a specific audience export. Use when you need to understand an audience export after it has been created or check its status. |
| `GOOGLE_ANALYTICS_GET_AUDIENCE_LIST` | Get Audience List | Tool to get configuration metadata about a specific audience list. Use after confirming the audience list resource name. |
| `GOOGLE_ANALYTICS_GET_CUSTOM_DIMENSION` | Get Custom Dimension | Tool to retrieve a single CustomDimension by its resource name. Use when you need detailed information about a specific custom dimension including its display name, scope, and parameter name. |
| `GOOGLE_ANALYTICS_GET_DATA_RETENTION_SETTINGS` | Get Data Retention Settings | Tool to retrieve data retention configuration for a Google Analytics property. Use when you need to check event-level and user-level data retention durations and reset settings. |
| `GOOGLE_ANALYTICS_GET_DATA_SHARING_SETTINGS` | Get Data Sharing Settings | Tool to retrieve data sharing configuration for a Google Analytics account. Use when you need to check which data sharing settings are enabled for an account, including sharing with Google support, sales teams, products, and benchmarking. |
| `GOOGLE_ANALYTICS_GET_GOOGLE_SIGNALS_SETTINGS` | Get Google Signals Settings | Tool to retrieve Google Signals configuration settings for a GA4 property. Use when you need to check whether Google Signals is enabled and the consent status for a property. |
| `GOOGLE_ANALYTICS_GET_KEY_EVENT` | Get Key Event | Tool to retrieve a Key Event. Use after confirming the key event resource name. Read-only; create, update, or delete operations require the Google Analytics UI. |
| `GOOGLE_ANALYTICS_GET_METADATA` | Get Metadata | Tool to get metadata for dimensions, metrics, and comparisons for a GA4 property. Use to discover available fields before building a report — always derive dimension/metric apiNames from this output rather than hardcoding from GA4 UI labels, which differ. Available fields vary per property; skip validation and downstream report tools like GOOGLE_ANALYTICS_RUN_REPORT return 400 INVALID_ARGUMENT on incompatible or invalid field combinations. Response can contain hundreds of fields; filter to relevant subset before passing to downstream logic. |
| `GOOGLE_ANALYTICS_GET_PROPERTY` | Get Property | Tool to retrieve a single GA4 Property by its resource name. Use when you need detailed property configuration including display name, time zone, currency, and other settings. |
| `GOOGLE_ANALYTICS_GET_PROPERTY_QUOTAS_SNAPSHOT` | Get Property Quotas Snapshot | Tool to retrieve all property quotas organized by category (corePropertyQuota, funnelPropertyQuota, realtimePropertyQuota) for a given GA4 property. Use when you need to check current quota usage. Snapshot data can lag real consumption by several minutes; treat reported values as approximate and avoid scheduling high-volume jobs at full apparent capacity. |
| `GOOGLE_ANALYTICS_GET_RECURRING_AUDIENCE_LIST` | Get Recurring Audience List | Tool to get configuration metadata about a specific recurring audience list. Use when you need to understand a recurring audience list's state after it has been created or to get the resource name of the most recent audience list instance. |
| `GOOGLE_ANALYTICS_GET_REPORT_TASK` | Get Report Task | Tool to get report metadata about a specific report task. Use after creating a report task to check its processing state or inspect its report definition. |
| `GOOGLE_ANALYTICS_LIST_ACCOUNT_SUMMARIES` | List Account Summaries | Tool to retrieve summaries of all Google Analytics accounts accessible by the caller. Use when you need a high-level overview of accounts and their properties without fetching full account details. |
| `GOOGLE_ANALYTICS_LIST_ACCOUNTS_V1_BETA` | List Accounts (v1beta) | Tool to list all Google Analytics accounts accessible by the caller using v1beta API. Use when you need to enumerate accounts. Note that these accounts might not have GA properties yet. Soft-deleted accounts are excluded by default. |
| `GOOGLE_ANALYTICS_LIST_ADSENSE_LINKS` | List AdSense Links | Tool to list all AdSenseLinks on a property. Use when you need to fetch all AdSense links for a given Google Analytics property. |
| `GOOGLE_ANALYTICS_LIST_AUDIENCE_EXPORTS` | List Audience Exports | Tool to list all audience exports for a property. Use when you need to find and reuse existing audience exports rather than creating new ones. |
| `GOOGLE_ANALYTICS_LIST_AUDIENCE_LISTS` | List Audience Lists | Tool to list all audience lists for a specified property to help find and reuse existing lists. Use when you need to retrieve a property's configured audience lists after confirming the property ID. |
| `GOOGLE_ANALYTICS_LIST_AUDIENCES` | List Audiences | Tool to list Audiences on a property. Use when you need to retrieve audience configurations for a Google Analytics property. Audiences created before 2020 may not be supported. |
| `GOOGLE_ANALYTICS_LIST_BIGQUERY_LINKS` | List BigQuery Links | Tool to list BigQuery Links on a property. Use when you need to retrieve BigQuery link resources associated with a Google Analytics property. Results support pagination for large datasets. |
| `GOOGLE_ANALYTICS_LIST_CALCULATED_METRICS` | List Calculated Metrics | List Calculated Metrics |
| `GOOGLE_ANALYTICS_LIST_CHANNEL_GROUPS` | List Channel Groups | Tool to list ChannelGroups on a property. Use when you need to retrieve channel groups that categorize traffic sources in Analytics reports. |
| `GOOGLE_ANALYTICS_LIST_CONVERSION_EVENTS` | List Conversion Events | Tool to list conversion events on a property. Use when you need to retrieve conversion events configured for a given property. |
| `GOOGLE_ANALYTICS_LIST_CUSTOM_DIMENSIONS` | List Custom Dimensions | List Custom Dimensions |
| `GOOGLE_ANALYTICS_LIST_CUSTOM_METRICS` | List Custom Metrics | Tool to list CustomMetrics on a property. Use when you need to retrieve all custom metrics configured for a given property. |
| `GOOGLE_ANALYTICS_LIST_DATA_STREAMS` | List DataStreams | Tool to list DataStreams on a property. Use when you need to retrieve data stream configurations for a Google Analytics property. |
| `GOOGLE_ANALYTICS_LIST_DV360_AD_LINKS` | List Display & Video 360 Advertiser Links | Tool to list Display & Video 360 advertiser links on a property. Use when you need to retrieve DisplayVideo360AdvertiserLink resources associated with a Google Analytics property. Results support pagination for large datasets. |
| `GOOGLE_ANALYTICS_LIST_DV360_LINK_PROPOSALS` | List DisplayVideo360 Advertiser Link Proposals | Tool to list DisplayVideo360AdvertiserLinkProposals on a property. Use when you need to retrieve Display & Video 360 advertiser link proposals associated with a Google Analytics property. Results support pagination for large datasets. |
| `GOOGLE_ANALYTICS_LIST_EVENT_CREATE_RULES` | List Event Create Rules | Tool to list EventCreateRules configured on a web data stream. Use when you need to retrieve event create rules for a specific GA4 property data stream. |
| `GOOGLE_ANALYTICS_LIST_EXPANDED_DATA_SETS` | List Expanded Data Sets | Tool to list ExpandedDataSets on a property. Use when you need to retrieve expanded data set configurations for a Google Analytics 360 property. |
| `GOOGLE_ANALYTICS_LIST_FIREBASE_LINKS` | List Firebase Links | Tool to list FirebaseLinks on a property. Use when you need to retrieve Firebase connections associated with a Google Analytics property. Each property can have at most one FirebaseLink. |
| `GOOGLE_ANALYTICS_LIST_GOOGLE_ADS_LINKS` | List Google Ads Links | Tool to list GoogleAdsLinks on a property. Use when you need to retrieve Google Ads account links configured for a Google Analytics property. Supports pagination for large result sets. |
| `GOOGLE_ANALYTICS_LIST_KEY_EVENTS` | List Key Events | Tool to list Key Events. Use when you need to retrieve all key event definitions for a given property. Key events are read-only via API; creation, updates, and deletion require the Google Analytics UI. An empty results list means no key events are configured, not a failure. Do not infer key-event status from report data (e.g., eventCount); use this tool to confirm. |
| `GOOGLE_ANALYTICS_LIST_MEASUREMENT_PROTOCOL_SECRETS` | List Measurement Protocol Secrets | Tool to list MeasurementProtocolSecrets under a data stream. Use when you need to retrieve measurement protocol secrets for server-side event tracking. |
| `GOOGLE_ANALYTICS_LIST_PROPERTIES_FILTERED` | List Property | Tool to list GA4 properties based on filter criteria. Use when you need to find properties under a specific parent account or with specific firebase projects. Supports pagination and including soft-deleted properties. |
| `GOOGLE_ANALYTICS_LIST_RECURRING_AUDIENCE_LISTS` | List Recurring Audience Lists | Tool to list all recurring audience lists for a GA4 property. Use when you need to find and reuse existing recurring audience lists. |
| `GOOGLE_ANALYTICS_LIST_REPORTING_DATA_ANNOTATIONS` | List Reporting Data Annotations | Tool to list all Reporting Data Annotations for a specific property. Use when you need to retrieve annotations that document important events or periods in GA4 reporting data. |
| `GOOGLE_ANALYTICS_LIST_REPORT_TASKS` | List Report Tasks | Tool to list all report tasks for a Google Analytics property. Use when you need to retrieve report task definitions and their execution status. |
| `GOOGLE_ANALYTICS_LIST_SEARCH_ADS360_LINKS` | List Search Ads 360 Links | Tool to list all SearchAds360Links on a property. Use when you need to retrieve all Search Ads 360 links for a given Google Analytics property. Supports pagination for large result sets. |
| `GOOGLE_ANALYTICS_LIST_SK_AD_NETWORK_CONVERSION_VALUE_SCHEMAS` | List SKAdNetwork Conversion Value Schemas | Tool to list SKAdNetworkConversionValueSchema configurations for an iOS data stream. Use when you need to retrieve conversion value schemas for iOS app tracking. Maximum one schema per property is supported. |
| `GOOGLE_ANALYTICS_LIST_SUBPROPERTY_EVENT_FILTERS` | List Subproperty Event Filters | Tool to list all subproperty event filters on a property. Use when you need to retrieve event filters that route events to subproperties. |
| `GOOGLE_ANALYTICS_LIST_SUBPROPERTY_SYNC_CONFIGS` | List Subproperty Sync Configs | Tool to list SubpropertySyncConfig resources for managing subproperty synchronization configurations. Use when you need to fetch subproperty sync configs for a GA4 property. |
| `GOOGLE_ANALYTICS_PROVISION_ACCOUNT_TICKET` | Provision Account Ticket | Tool to request a ticket for creating a Google Analytics account. Use when you need to initiate the account creation flow that requires user acceptance of Terms of Service. |
| `GOOGLE_ANALYTICS_QUERY_AUDIENCE_EXPORT` | Query Audience Export | Tool to query a completed audience export. Use when you need to fetch user rows with pagination. |
| `GOOGLE_ANALYTICS_QUERY_AUDIENCE_LIST` | Query Audience List | Tool to query an audience list. Use when you need to retrieve user rows from a GA4 audience list with pagination. |
| `GOOGLE_ANALYTICS_QUERY_REPORT_TASK` | Query Report Task | Tool to retrieve a report task's content. Use this after creating a report task with CreateReportTask and confirming it is in ACTIVE state. This method returns an error if the report task's state is not ACTIVE. |
| `GOOGLE_ANALYTICS_RUN_FUNNEL_REPORT` | Run Funnel Report | Tool to run a GA4 funnel report. Use when you need a customized funnel analysis report for a given property. Funnel step sequence is determined by step attributes in the response, not row order. |
| `GOOGLE_ANALYTICS_RUN_PIVOT_REPORT` | Run Pivot Report | Tool to run a customized pivot report of Google Analytics event data. Use when you need a pivot table view with advanced segmentation and multi-dimensional analysis of GA4 data. |
| `GOOGLE_ANALYTICS_RUN_REALTIME_REPORT` | Run Realtime Report | Tool to run a customized realtime report of Google Analytics event data. Use when you need realtime data (last 30-60 minutes) with dimensions and metrics for a GA4 property. |
| `GOOGLE_ANALYTICS_RUN_REPORT` | Run Report | Tool to run a customized GA4 data report. Use when you need event data after specifying dimensions, metrics, and date ranges. IMPORTANT - DIMENSION/METRIC COMPATIBILITY: The Google Analytics Data API has strict compatibility rules between dimensions and metrics. Not all combinations are valid. If you receive a 400 error with a message about incompatible dimensions/metrics, use the GOOGLE_ANALYTICS_CHECK_COMPATIBILITY action first to validate your dimension/metric combinations before running reports. Common incompatibilities include: - Demographic dimensions (userAgeBracket, userGender) with session-scoped dimensions/filters (sessionCampaignName, sessionSource) - Certain user-scoped dimensions with event-scoped metrics For complex queries, consider starting with simpler dimension/metric combinations or use CHECK_COMPATIBILITY to pre-validate your request. |
| `GOOGLE_ANALYTICS_SEND_EVENTS` | Send Events | Tool to send event data to Google Analytics 4 using the Measurement Protocol. Use when you need to track server-side events that supplement client-side gtag.js or Firebase tracking. The Measurement Protocol allows sending event data directly to GA4 from servers, applications, or other devices. Events are processed asynchronously and typically appear in reports within 24-48 hours. For validation, use the validation server endpoint first (mp/collect/validate). |
| `GOOGLE_ANALYTICS_UPDATE_PROPERTY` | Update Property | Tool to update an existing GA4 Property. Use when you need to modify property settings such as display name, time zone, currency code, or industry category. |
| `GOOGLE_ANALYTICS_VALIDATE_EVENTS` | Validate Events | Tool to validate Measurement Protocol events before sending them to production. Use when you need to verify event structure and parameters are correct before sending real data. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Google Analytics MCP server is an implementation of the Model Context Protocol that connects your AI agent to Google Analytics. It provides structured and secure access so your agent can perform Google Analytics operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A Google Analytics account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Google Analytics

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for Google Analytics access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, google analytics)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available Google Analytics tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["google_analytics"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Google Analytics actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Google Analytics actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["google_analytics"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Google Analytics actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to Google Analytics
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Google Analytics, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["google_analytics"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Google Analytics actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Google Analytics actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["google_analytics"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Google Analytics actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Google Analytics to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Google Analytics tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## How to build Google Analytics MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/google_analytics/framework/chatgpt)
- [Antigravity](https://composio.dev/toolkits/google_analytics/framework/antigravity)
- [OpenAI Agents SDK](https://composio.dev/toolkits/google_analytics/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/google_analytics/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/google_analytics/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/google_analytics/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/google_analytics/framework/codex)
- [Cursor](https://composio.dev/toolkits/google_analytics/framework/cursor)
- [VS Code](https://composio.dev/toolkits/google_analytics/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/google_analytics/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/google_analytics/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/google_analytics/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/google_analytics/framework/cli)
- [Google ADK](https://composio.dev/toolkits/google_analytics/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/google_analytics/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/google_analytics/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/google_analytics/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/google_analytics/framework/crew-ai)

## Related Toolkits

- [Firecrawl](https://composio.dev/toolkits/firecrawl) - Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources.
- [Tavily](https://composio.dev/toolkits/tavily) - Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research.
- [Exa](https://composio.dev/toolkits/exa) - Exa is a data extraction and search platform for gathering and analyzing information from websites, APIs, or databases. It helps teams quickly surface insights and automate data-driven workflows.
- [Serpapi](https://composio.dev/toolkits/serpapi) - SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research.
- [Peopledatalabs](https://composio.dev/toolkits/peopledatalabs) - Peopledatalabs delivers B2B data enrichment and identity resolution APIs. Supercharge your apps with accurate, up-to-date business and contact data.
- [Snowflake](https://composio.dev/toolkits/snowflake) - Snowflake is a cloud data warehouse built for elastic scaling, secure data sharing, and fast SQL analytics across major clouds.
- [Posthog](https://composio.dev/toolkits/posthog) - PostHog is an open-source analytics platform for tracking user interactions and product metrics. It helps teams refine features, analyze funnels, and reduce churn with actionable insights.
- [Amplitude](https://composio.dev/toolkits/amplitude) - Amplitude is a digital analytics platform for product and behavioral data insights. It helps teams analyze user journeys and make data-driven decisions quickly.
- [Bright Data MCP](https://composio.dev/toolkits/brightdata_mcp) - Bright Data MCP is an AI-powered web scraping and data collection platform. Instantly access public web data in real time with advanced scraping tools.
- [Browseai](https://composio.dev/toolkits/browseai) - Browseai is a web automation and data extraction platform that turns any website into an API. It's perfect for monitoring websites and retrieving structured data without manual scraping.
- [ClickHouse](https://composio.dev/toolkits/clickhouse) - ClickHouse is an open-source, column-oriented database for real-time analytics and big data processing using SQL. Its lightning-fast query performance makes it ideal for handling large datasets and delivering instant insights.
- [Coinmarketcal](https://composio.dev/toolkits/coinmarketcal) - CoinMarketCal is a community-powered crypto calendar for upcoming events, announcements, and releases. It helps traders track market-moving developments and stay ahead in the crypto space.
- [Control d](https://composio.dev/toolkits/control_d) - Control d is a customizable DNS filtering and traffic redirection platform. It helps you manage internet access, enforce policies, and monitor usage across devices and networks.
- [Databox](https://composio.dev/toolkits/databox) - Databox is a business analytics platform that connects your data from any tool and device. It helps you track KPIs, build dashboards, and discover actionable insights.
- [Databricks](https://composio.dev/toolkits/databricks) - Databricks is a unified analytics platform for big data and AI on the lakehouse architecture. It empowers data teams to collaborate, analyze, and build scalable solutions efficiently.
- [Datagma](https://composio.dev/toolkits/datagma) - Datagma delivers data intelligence and analytics for business growth and market discovery. Get actionable market insights and track competitors to inform your strategy.
- [Delighted](https://composio.dev/toolkits/delighted) - Delighted is a customer feedback platform based on the Net Promoter System®. It helps you quickly gather, track, and act on customer sentiment.
- [Dovetail](https://composio.dev/toolkits/dovetail) - Dovetail is a research analysis platform for transcript review and insight generation. It helps teams code interviews, analyze feedback, and create actionable research summaries.
- [Dub](https://composio.dev/toolkits/dub) - Dub is a short link management platform with analytics and API access. Use it to easily create, manage, and track branded short links for your business.
- [Elasticsearch](https://composio.dev/toolkits/elasticsearch) - Elasticsearch is a distributed, RESTful search and analytics engine for all types of data. It delivers fast, scalable search and powerful analytics across massive datasets.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Google Analytics MCP?

With a standalone Google Analytics MCP server, the agents and LLMs can only access a fixed set of Google Analytics tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Google Analytics and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Google Analytics tools.

### Can I manage the permissions and scopes for Google Analytics while using Tool Router?

Yes, absolutely. You can configure which Google Analytics scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Google Analytics data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)