How to integrate Gosquared MCP with OpenAI Agents SDK

Framework Integration Gradient
Gosquared Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Gosquared to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Gosquared agent that can list all websites linked to my account, show active chat conversations from today, add a new shared user by email, delete a person and blacklist them through natural language commands.

This guide will help you understand how to give your OpenAI Agents 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.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Gosquared
  • Configure an AI agent that can use Gosquared as a tool
  • Run a live chat session where you can ask the agent to perform Gosquared operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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 userTool to remove a user from a GoSquared project.
Account Shared UsersTool to retrieve all team members that have access to a given project.
List Account SitesTool to list 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.
Retrieve Chat ConversationTool to retrieve a chat conversation by its ID.
Retrieve Chat MessagesTool to retrieve a list of messages from a chat conversation.
Retrieve Chat ConversationsTool to retrieve chat data for reporting purposes.
Retrieve Chat FeedTool to retrieve messages and events from a chat conversation.
Delete personTool to delete a person profile and all associated data.
Get specific chat messageTool to retrieve a specific chat message.
Get Specific VisitorTool to retrieve information for a specific online visitor.
Get People Event TypesTool to retrieve event types ordered by tracked count.
Get People Property TypesTool to retrieve all property types in People CRM.
Get PersonTool to retrieve a specific person profile by ID.
GoSquared - Get Person FeedTool to retrieve a specific person's event feed in reverse chronological order.
List PeopleTool to search and filter People CRM profiles.
Get current concurrent visitorsTool to retrieve the number of concurrent visitors currently on your site.
Get Real-Time Popular PagesTool to retrieve the most popular pages currently being viewed on your site.
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 Time SeriesTool to retrieve visitor counts over time as data points.
Get Real-Time Online VisitorsTool to retrieve a list of current online visitors.
GoSquared - People DevicesTool to retrieve device information from People CRM.
Export Smart Group FeedTool to export all pageview activity for a Smart Group to CSV.
Smart Group PeopleTool to retrieve people in a specific Smart Group.
List People SmartGroupsTool to retrieve all Smart Groups for a project.
Add Account SiteTool to add a new site to the GoSquared account.
Archive Chat ConversationTool to archive a chat conversation.
Send Chat MessageTool to send a message in a chat conversation.
Leave Chat NoteTool to leave a note in a chat conversation.
Unarchive Chat ConversationTool to unarchive a chat conversation.
Create People SmartGroupTool to add a new Smart Group to a GoSquared project.
Track GoSquared EventTool to send custom events to GoSquared.
Track GoSquared IdentifyTool to identify users and associate them with specific properties in GoSquared.
Track PageviewTool to track pageviews.
Track GoSquared TransactionTool to track e-commerce transactions.
Retrieve Aggregate MetricsTool to retrieve aggregate metrics for a specified period.
Get Campaign Medium MetricsTool to retrieve UTM medium metrics over a time period.
Retrieve Event CountsTool to retrieve counts of event triggers over a specified time period.
Get Page MetricsTool to retrieve page-level metrics over a specified period.
Get Base Path MetricsTool to retrieve base path metrics over a time period.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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 starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Gosquared project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Gosquared.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Gosquared Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["gosquared"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only gosquared.
  • The router checks the user's Gosquared connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Gosquared.
  • This approach keeps things lightweight and lets the agent request Gosquared tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Gosquared. "
        "Help users perform Gosquared operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Gosquared and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Gosquared operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Gosquared.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Gosquared and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["gosquared"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Gosquared. "
        "Help users perform Gosquared operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Gosquared MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Gosquared.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

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 OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
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.