How to integrate Iterate MCP with OpenAI Agents SDK

This guide walks you through connecting Iterate to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Iterate agent that can list your surveys, add survey recipients, review responses, search company users, and delete user data through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Iterate account through Composio's Iterate MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Iterate logoIterate
Api Key

Iterate is a customer feedback platform for distributing surveys, analyzing responses, and managing user privacy data. It helps teams collect customer feedback, spot trends, and keep privacy workflows organized.

13 Tools

Introduction

This guide walks you through connecting Iterate to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Iterate agent that can list your surveys, add survey recipients, review responses, search company users, and delete user data through natural language commands.

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

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

Also integrate Iterate with

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 Iterate
  • Configure an AI agent that can use Iterate as a tool
  • Run a live chat session where you can ask the agent to perform Iterate operations

What is OpenAI 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 Iterate MCP server, and what's possible with it?

The Iterate MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Iterate account. It provides structured and secure access to your surveys, recipients, responses, statistics, and company user data, so your agent can distribute surveys, review feedback, analyze performance, find users, and manage privacy requests on your behalf.

  • Survey distribution: Have your agent add one recipient or import a batch, then send the survey now or schedule it for later.
  • Survey review: Let the agent list your surveys and retrieve a survey's configuration and questions.
  • Feedback analysis: Instruct your agent to review completed submissions, inspect individual answers within a date range, and check delivery, response count, and response rate statistics.
  • Company user search: Direct your agent to find a company user by email, external reference, or profile property and review their survey participation totals.
  • Privacy data management: Have your agent anonymize identifying details while retaining responses, or permanently delete selected users and their survey responses.

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

What is Composio SDK?

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

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

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

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

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Iterate project
  • Some knowledge of Python or Typescript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

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.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
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 Iterate.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Iterate
const session = await composio.create(userId as string, {
  toolkits: ['iterate'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only iterate.
  • The router checks the user's Iterate connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Iterate.
  • This approach keeps things lightweight and lets the agent request Iterate tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Iterate. Help users perform Iterate operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: '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 Iterate 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 object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Iterate operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

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

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Iterate.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Iterate and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['iterate'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Iterate. Help users perform Iterate operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

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

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

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

Conclusion

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

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.
TOOLS

Supported Tools

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

Add Survey Recipient

Add one email recipient to a survey for a later send without sending the survey now.

Anonymize Company User

Irreversibly remove one Iterate user's email and attributes while retaining survey responses.

Bulk Anonymize Company Users

Irreversibly remove identifying data from every Iterate company user matching at least one explicit email, external-ID, or typed user-property selector while retaining survey responses.

Bulk Delete Company User Data

Permanently delete every matching Iterate company user and all matching users' survey responses using explicit non-empty selectors.

Delete Company User Data

Permanently delete one Iterate user object and all of that user's survey responses.

Get Survey

Return one survey's configuration and questions by survey ID.

Get Survey Stats

Return delivery, display, response-count, and response-rate statistics for one survey.

Import Survey Recipients

Add a non-empty batch of email recipients to a survey without sending it, and return duplicate, failure, and success counts.

List Survey Response Groups

Return one reverse-chronological page of completed survey submissions grouped by user, plus a continuation cursor.

List Survey Responses

Return one reverse-chronological page of individual answers for a survey, with an optional date range and continuation cursor.

List Surveys

Return all surveys available to the connected Iterate API key, including the survey and company IDs needed by other tools.

Search Company Users

Find one user in the connected Iterate company by email, external ID, or one typed user property and return survey participation totals.

Send Survey

Irreversibly send or schedule an email survey to one specified recipient or every previously added recipient.

FAQ

Frequently asked questions

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

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 Iterate tools.

Yes, absolutely. You can configure which Iterate 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.

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 Iterate data and credentials are handled as safely as possible.

Start with Iterate.It takes 30 seconds.

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

Start building