How to integrate Gosquared MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Gosquared logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Gosquared to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Gosquared agent that can list all websites linked to your account, show active chat conversations from today, add a new shared user by email through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Gosquared account through Composio's Gosquared MCP server.

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

Also integrate Gosquared with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Gosquared integration
  • Using Composio's Tool Router to dynamically load and access Gosquared 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 Gosquared MCP server, and what's possible with it?

The Gosquared MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Gosquared account. It provides structured and secure access to your real-time web analytics and customer engagement data, so your agent can perform actions like managing team members, analyzing chat conversations, retrieving site data, and handling customer profiles on your behalf.

  • Team member management: Seamlessly add or remove shared users from your GoSquared projects, making it easy to control who has access to your analytics and engagement tools.
  • Insightful chat analytics: Retrieve chat conversations, messages, and conversation feeds, enabling your agent to analyze customer interactions and surface important chat history.
  • Project and site listing: Quickly list all sites and projects accessible to your account, so your assistant can pull structured data about your web properties.
  • API key validation and security checks: Verify API key validity and scopes to ensure secure, authorized access before performing sensitive operations.
  • Customer profile management: Delete person records, including all associated data, when you need to manage your user database or enforce data privacy requests.

Supported Tools & Triggers

Tools
Add Shared UserTool to add a new shared user to a project.
Remove shared userRemoves a shared user from a GoSquared project by their email address, revoking their access to the site.
Account Shared UsersRetrieves all team members who have access to the current GoSquared project.
List Account SitesList all projects/sites accessible to the authenticated account.
Check API Token Validity and ScopesTool to check whether an API key is valid and retrieve its enabled scopes.
Block VisitorTool to block a specific visitor from being tracked.
Retrieve Chat ConversationRetrieve detailed information about a chat conversation by its ID.
Retrieve Chat MessagesRetrieve messages from a GoSquared chat conversation by chat ID.
Retrieve Chat ConversationsTool to retrieve chat data for reporting purposes.
Retrieve Chat FeedRetrieve the complete feed of messages and events from a chat conversation.
Create Account WebhookTool to create a webhook to receive notifications about events in a GoSquared project.
Create Webhook TriggerTool to add a trigger to an existing GoSquared webhook.
Delete Account WebhookTool to delete a webhook from a GoSquared account.
Delete personTool to delete a person profile and all associated data.
Timeout Visitor SessionsTool to end all tracking sessions for a specified visitor in GoSquared.
Get Account Blocked ItemsTool to retrieve a list of blocked IP addresses, bots, and visitors for a project.
Get Account Blocked BotsTool to retrieve the bot blocking status for a GoSquared project.
Get Blocked IP AddressesTool to retrieve the list of blocked IP addresses for the account.
Get Account Blocked VisitorsTool to retrieve visitor IDs that have been blocked for a project.
Get Account Site DetailsTool to retrieve detailed information about a specific site/project by its site_token.
Get Account Sites UsageTool to retrieve all sites and their pageview counts for the authenticated account.
Get Account Tagged VisitorsTool to retrieve the list of tagged visitors from the account.
Get Account Trigger TypeTool to retrieve details of a specific trigger type from GoSquared.
Get Account Trigger TypesTool to retrieve available types of triggers in GoSquared.
Get Account WebhookTool to retrieve a specific webhook by ID from a GoSquared account.
Get Account WebhooksRetrieves a list of webhooks configured for the GoSquared project.
Get Account Webhook TriggersRetrieves all triggers for a webhook.
Get Specific Chat MessageRetrieve a specific chat message by its message ID from a chat conversation.
Get Real-Time Visitor BrowsersTool to retrieve browsers used by currently online visitors, sorted by visitor count.
Get Real-Time CampaignsTool to retrieve currently running campaigns with real-time visitor counts.
Get Real-Time Visitor CountriesTool to retrieve countries where currently online visitors are located, sorted by visitor count.
Get Real-Time EngagementTool to retrieve engagement information of currently online users.
Get Real-Time Visitor Geo LocationsTool to retrieve real-time geographic coordinates for currently online visitors.
Get Real-Time Visitor LanguagesTool to retrieve languages for currently online visitors sorted by visitor count.
Get Now NotificationsTool to retrieve notifications stored in GoSquared.
Get Real-Time OrganisationsTool to retrieve internet organisations currently being used by online visitors, sorted by visitor count.
Get Now Sources By SectionTool to retrieve a specific group of real-time traffic sources such as 'site', 'organic', or 'social'.
Get Current TimeTool to retrieve the current time according to GoSquared infrastructure.
Get Specific VisitorRetrieves real-time session information for a specific online visitor.
Get People Event TypesRetrieve all event types tracked in GoSquared People CRM, ordered by frequency.
Get People Property TypesRetrieve property types (schema definitions) from GoSquared People CRM.
Get Person ProfileRetrieve a specific person's profile from GoSquared People CRM by their unique ID.
GoSquared - Get Person FeedRetrieve a person's complete event feed from GoSquared People CRM.
Get Browser MetricsTool to retrieve summarised browser metrics over a specified time period.
Get Campaign Content MetricsRetrieve UTM content metrics (utm_content) aggregated over a specified date range.
Get Campaign Name MetricsRetrieve UTM campaign name metrics (utm_campaign) aggregated over a specified date range.
Get Campaign Source MetricsRetrieve UTM source metrics (utm_source) aggregated over a specified date range.
Get Campaign Term MetricsRetrieve UTM term metrics (utm_term) aggregated over a specified date range.
Get Category MetricsTool to retrieve summarised category metrics over a specified time period.
Get Country MetricsRetrieve country-level visit metrics aggregated over a specified date range.
Get Language MetricsRetrieve summarised language metrics over a given time period.
Get Organisation MetricsTool to retrieve summarised organisation metrics over a given time period.
Get Operating System MetricsTool to retrieve summarised operating system metrics over a specified time period.
Get Product MetricsTool to retrieve summarised product metrics over a specified time period.
Get Screen Dimensions MetricsTool to retrieve summarised screen dimensions metrics over a specified time period.
Get Traffic Sources MetricsTool to retrieve a historical list of traffic sources that referred visitors to the site over a specified period.
Get Trends Sources By TypeTool to retrieve a historical list of sources for the given section type.
Get Transaction MetricsTool to retrieve summarised transaction metrics over a specified time period.
List PeopleSearch and filter tracked people in GoSquared People CRM.
Get current concurrent visitorsTool to retrieve the number of concurrent visitors currently on your site.
Get Real-Time Popular PagesRetrieve the most popular pages currently being viewed on your site in real-time.
Get Real-Time Visitor PlatformsTool to retrieve platforms used by online visitors sorted by visitor count.
Get Real-Time OverviewTool to retrieve a summary of real-time data for the site.
Now SourcesTool to retrieve the most influential traffic sources currently driving visitors to your site.
Get Visitor Time SeriesRetrieves time series data showing the number of concurrent visitors to your site over time.
Get Real-Time Online VisitorsTool to retrieve a list of current online visitors.
GoSquared - List All DevicesRetrieve a paginated list of all devices tracked in GoSquared People CRM.
Export Smart Group FeedExport all pageview activity for users in a Smart Group to a downloadable CSV file.
Smart Group PeopleRetrieve people (user profiles) from a specific Smart Group in GoSquared People CRM.
List People Smart GroupsRetrieve all Smart Groups for a GoSquared People CRM project.
Add Account SiteCreates a new site/project in the GoSquared account for analytics tracking.
Archive Chat ConversationArchives a chat conversation in GoSquared Inbox.
Send Chat MessageSend a message to a visitor in a GoSquared chat conversation.
Leave Chat NoteAdds an internal note to a GoSquared chat conversation.
Unarchive Chat ConversationUnarchives a chat conversation in GoSquared Inbox.
Create People SmartGroupCreate a new Smart Group in GoSquared People CRM to segment users by custom criteria.
Send Tracking PingSends a ping to keep the visitor session active in GoSquared.
Tag VisitorTool to add a tag to an identified visitor in GoSquared.
Track GoSquared EventTrack custom events in GoSquared analytics.
Identify UserIdentify a user in GoSquared and set their profile properties.
Track PageviewTracks a pageview event in GoSquared Analytics.
Track GoSquared TransactionTrack e-commerce transactions in GoSquared analytics.
Track User PropertiesTrack user properties for a visitor in GoSquared.
Retrieve Aggregate MetricsRetrieve aggregate web analytics metrics for a specified time period.
Get Campaign Medium MetricsRetrieve UTM medium metrics (utm_medium) aggregated over a specified date range.
Retrieve Event CountsRetrieve counts of tracked event triggers over a specified time period.
Get Page MetricsRetrieve page-level visit metrics over a specified time period.
Get Base Path MetricsRetrieves base path metrics (first URL path segments) over a time period.
Update Account Blocked BotsTool to update the automatic bot blocking feature for a project.
Update Account Blocked IPsTool to update the list of IP addresses to be blocked for a GoSquared project.

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: ["gosquared"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Gosquared 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 Gosquared-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 Gosquared 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 gosquared, 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 Gosquared 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 Gosquared 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: ["gosquared"],
  });

  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 gosquared, 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 Gosquared 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 Gosquared MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Gosquared MCP?

With a standalone Gosquared MCP server, the agents and LLMs can only access a fixed set of Gosquared tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Gosquared 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 Gosquared tools.

Can I manage the permissions and scopes for Gosquared while using Tool Router?

Yes, absolutely. You can configure which Gosquared 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 Gosquared 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.