How to integrate Google Analytics MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Google Analytics logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Google Analytics to Vercel AI SDK v6 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 Vercel AI SDK 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

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Google Analytics integration
  • Using Composio's Tool Router to dynamically load and access Google Analytics tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

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 & Triggers

Tools
Archive Custom DimensionTool to archive a CustomDimension on a property.
Batch Run Pivot ReportsTool to return multiple pivot reports in a batch for a GA4 property.
Batch Run ReportsTool to return multiple analytics data reports in a batch.
Check CompatibilityTool to list dimensions and metrics compatible with a GA4 report request.
Create Audience ExportTool to create an audience export for Google Analytics.
Create Audience ListTool to create an audience list for later retrieval by initiating a long-running asynchronous request.
Create Custom DimensionTool to create a CustomDimension for a Google Analytics property.
Create Custom MetricTool to create a custom metric in Google Analytics.
Create Expanded Data SetTool to create an expanded data set for a property.
Create Recurring Audience ListTool to create a recurring audience list that automatically generates new audience lists daily based on the latest data.
Create Report TaskTool to create a report task as a long-running asynchronous request for customized Google Analytics event data reports.
Create Rollup PropertyTool to create a roll-up property.
Get AccountTool to retrieve a single Account by its resource name.
Get Attribution SettingsTool to retrieve attribution configuration for a Google Analytics property.
Get AudienceTool to retrieve a single Audience configuration from a Google Analytics property.
Get Audience ExportTool to get configuration metadata about a specific audience export.
Get Audience ListTool to get configuration metadata about a specific audience list.
Get Custom DimensionTool to retrieve a single CustomDimension by its resource name.
Get Data Retention SettingsTool to retrieve data retention configuration for a Google Analytics property.
Get Data Sharing SettingsTool to retrieve data sharing configuration for a Google Analytics account.
Get Google Signals SettingsTool to retrieve Google Signals configuration settings for a GA4 property.
Get Key EventTool to retrieve a Key Event.
Get MetadataTool to get metadata for dimensions, metrics, and comparisons for a GA4 property.
Get PropertyTool to retrieve a single GA4 Property by its resource name.
Get Property Quotas SnapshotTool to retrieve all property quotas organized by category (corePropertyQuota, funnelPropertyQuota, realtimePropertyQuota) for a given GA4 property.
Get Recurring Audience ListTool to get configuration metadata about a specific recurring audience list.
Get Report TaskTool to get report metadata about a specific report task.
List Account SummariesTool to retrieve summaries of all Google Analytics accounts accessible by the caller.
List Accounts (v1beta)Tool to list all Google Analytics accounts accessible by the caller using v1beta API.
List AdSense LinksTool to list all AdSenseLinks on a property.
List Audience ExportsTool to list all audience exports for a property.
List Audience ListsTool to list all audience lists for a specified property to help find and reuse existing lists.
List AudiencesTool to list Audiences on a property.
List BigQuery LinksTool to list BigQuery Links on a property.
List Calculated MetricsList Calculated Metrics
List Channel GroupsTool to list ChannelGroups on a property.
List Conversion EventsTool to list conversion events on a property.
List Custom DimensionsList Custom Dimensions
List Custom MetricsTool to list CustomMetrics on a property.
List DataStreamsTool to list DataStreams on a property.
List Display & Video 360 Advertiser LinksTool to list Display & Video 360 advertiser links on a property.
List DisplayVideo360 Advertiser Link ProposalsTool to list DisplayVideo360AdvertiserLinkProposals on a property.
List Event Create RulesTool to list EventCreateRules configured on a web data stream.
List Expanded Data SetsTool to list ExpandedDataSets on a property.
List Firebase LinksTool to list FirebaseLinks on a property.
List Google Ads LinksTool to list GoogleAdsLinks on a property.
List Key EventsTool to list Key Events.
List Measurement Protocol SecretsTool to list MeasurementProtocolSecrets under a data stream.
List PropertyTool to list GA4 properties based on filter criteria.
List Recurring Audience ListsTool to list all recurring audience lists for a GA4 property.
List Reporting Data AnnotationsTool to list all Reporting Data Annotations for a specific property.
List Report TasksTool to list all report tasks for a Google Analytics property.
List Search Ads 360 LinksTool to list all SearchAds360Links on a property.
List SKAdNetwork Conversion Value SchemasTool to list SKAdNetworkConversionValueSchema configurations for an iOS data stream.
List Subproperty Event FiltersTool to list all subproperty event filters on a property.
List Subproperty Sync ConfigsTool to list SubpropertySyncConfig resources for managing subproperty synchronization configurations.
Provision Account TicketTool to request a ticket for creating a Google Analytics account.
Query Audience ExportTool to query a completed audience export.
Query Audience ListTool to query an audience list.
Query Report TaskTool to retrieve a report task's content.
Run Funnel ReportTool to run a GA4 funnel report.
Run Pivot ReportTool to run a customized pivot report of Google Analytics event data.
Run Realtime ReportTool to run a customized realtime report of Google Analytics event data.
Run ReportTool to run a customized GA4 data report.
Send EventsTool to send event data to Google Analytics 4 using the Measurement Protocol.
Update PropertyTool to update an existing GA4 Property.
Validate EventsTool to validate Measurement Protocol events before sending them to production.

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

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

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.

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["google_analytics"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Google Analytics tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Google Analytics-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Google Analytics tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to google_analytics, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Google Analytics tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Google Analytics and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["google_analytics"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to google_analytics, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Google Analytics agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Google Analytics MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Google Analytics MCP with ChatGPT

Antigravity logo

Antigravity

Use Google Analytics MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Google Analytics MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Google Analytics MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Google Analytics MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Google Analytics MCP with Claude Cowork

Codex logo

Codex

Use Google Analytics MCP with Codex

Cursor logo

Cursor

Use Google Analytics MCP with Cursor

OpenClaw logo

OpenClaw

Use Google Analytics MCP with OpenClaw

Hermes logo

Hermes

Use Google Analytics MCP with Hermes

CLI logo

CLI

Use Google Analytics MCP with CLI

Google ADK logo

Google ADK

Use Google Analytics MCP with Google ADK

LangChain logo

LangChain

Use Google Analytics MCP with LangChain

Mastra AI logo

Mastra AI

Use Google Analytics MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Google Analytics MCP with LlamaIndex

CrewAI logo

CrewAI

Use Google Analytics MCP with CrewAI

OpenCode logo

OpenCode

Use Google Analytics MCP with OpenCode

VS Code logo

VS Code

Use Google Analytics MCP with VS Code

FAQ

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 Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 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.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗