How to integrate Heights Platform MCP with OpenAI Agents SDK

This guide walks you through connecting Heights Platform to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Heights Platform agent that can enroll students, track course progress, review your orders, grant access, and list submissions through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Heights Platform account through Composio's Heights Platform MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Heights Platform logoHeights Platform
Api Key

Heights Platform is an online course, digital product, and community platform for creators. It helps you sell learning products, manage students, track orders, and control access in one place.

16 Tools

Introduction

This guide walks you through connecting Heights Platform to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Heights Platform agent that can enroll students, track course progress, review your orders, grant access, and list submissions through natural language commands.

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

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

Also integrate Heights Platform 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 Heights Platform
  • Configure an AI agent that can use Heights Platform as a tool
  • Run a live chat session where you can ask the agent to perform Heights Platform 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 Heights Platform MCP server, and what's possible with it?

The Heights Platform MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Heights Platform account. It provides structured and secure access to your students, learning products, orders, course progress, and submissions, so your agent can manage enrollments, control course access, review progress, track orders, and inspect student work on your behalf.

  • Student enrollment and account management: Have your agent enroll students, view their account details and learning activity, or end their paid membership.
  • Course and bundle access control: Let the agent grant or revoke student access to courses and bundles based on your instructions.
  • Learning progress and submission review: Direct your agent to check course completion, list assignment answers or project posts, and reset saved progress when needed.
  • Product and order tracking: Instruct your agent to list published courses, bundles, and digital products, then review orders by status, student, or creation time.
  • Student role administration: Have your agent list available course roles, grant a role to a student, or revoke one when responsibilities change.

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 Heights Platform 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 Heights Platform.
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 Heights Platform
const session = await composio.create(userId as string, {
  toolkits: ['heights_platform'],
});
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 heights_platform.
  • The router checks the user's Heights Platform connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Heights Platform.
  • This approach keeps things lightweight and lets the agent request Heights Platform 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 Heights Platform. Help users perform Heights Platform 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 Heights Platform 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 Heights Platform 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 Heights Platform.
  • 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 Heights Platform 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: ['heights_platform'],
  });
  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 Heights Platform. Help users perform Heights Platform 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 Heights Platform MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Heights Platform.

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 Heights Platform action and event your agent gets out of the box.

Enroll Student

Create a student or update an existing student and mark them enrolled without granting course or bundle access.

Get Learning Product

Get detailed metadata for one course, bundle, or digital product by ID.

Get Order

Get one Heights order by its public unique order ID.

Get Student Course Progress

Get a student's overall and course-specific completion percentages for one course.

Get Student Details

Get a student by email, including account attributes, activity counts, paid orders, and enrolled courses.

Grant Student Access

Grant one course or bundle to a student by creating a zero-dollar paid order.

Grant Student Role

Grant one Heights role to a student, changing the student's authorization.

List Course Roles

List the Heights roles that can be granted to students.

List Learning Products

List published courses, bundles, or digital products in the connected Heights account.

List Orders

List Heights orders with optional status, student email, and creation-time filters, returning one page and an opaque continuation cursor.

List Students

List all Heights students one page at a time, or list the unpaginated students whose total completion is at least 100 percent.

List Student Submissions

List assignment answers or project posts submitted by students.

Reset Student Progress

Permanently erase a student's saved completion and progress records.

Revoke Student Access

Permanently remove one course or bundle from a student's existing orders.

Revoke Student Role

Revoke one Heights role from a student, changing the student's authorization.

Unenroll Student

End a student's paid membership by setting their Heights paying-student state to false.

FAQ

Frequently asked questions

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

Yes, absolutely. You can configure which Heights Platform 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 Heights Platform data and credentials are handled as safely as possible.

Start with Heights Platform.It takes 30 seconds.

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

Start building