How to integrate Google Classroom MCP with OpenAI Agents SDK

This guide walks you through connecting Google Classroom to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Google Classroom agent that can list all active courses for this teacher, create a new announcement in math class, get details for course id 12345 through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Google Classroom account through Composio's Google Classroom MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Google Classroom logoGoogle Classroom
Oauth2

Google Classroom is a free web service for educators and students to manage assignments and communication. It streamlines classroom collaboration and grading, making teaching simpler and more connected.

62 Tools

Introduction

This guide walks you through connecting Google Classroom to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Google Classroom agent that can list all active courses for this teacher, create a new announcement in math class, get details for course id 12345 through natural language commands.

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

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

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

The Google Classroom 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 Classroom account. It provides structured and secure access to your classes, assignments, and announcements, so your agent can list courses, manage announcements, create coursework, and handle classroom organization on your behalf.

  • Course and class management: Effortlessly create, list, or delete courses, and get detailed information about any class you manage or attend.
  • Announcement automation: Let your agent create, update, list, or remove announcements in specific courses—keeping students and teachers in the loop.
  • Coursework material handling: Quickly list all coursework materials in a class, so you can track resources and assignments with ease.
  • Streamlined assignment workflows: Organize and distribute assignments and resources, helping automate typical classroom tasks for educators and students.
  • Classroom insights retrieval: Fetch up-to-date details about classes and their structure, enabling your agent to provide summaries or help with enrollment decisions.

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

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 Google Classroom action and event your agent gets out of the box.

Create Course Alias

Tool to create an alias for a course.

Delete Course Alias

Tool to delete an alias of a course.

List Course Aliases

Tool to list aliases for a course.

Create Announcement

Tool to create an announcement in a course.

Delete Announcement

Tool to delete an announcement.

Get Announcement

Tool to get an announcement.

Get Add-on Context for Announcement

Tool to get metadata for Classroom add-ons in the context of a specific announcement post.

List Announcements

Tool to list announcements in a course.

Modify Announcement Assignees

Tool to modify assignee mode and options of an announcement.

Patch Announcement

Tool to update fields of an announcement.

Delete Add-on Attachment

Tool to delete an add-on attachment from a course announcement.

Get Add-on Attachment

Tool to get an add-on attachment from an announcement.

List Add-on Attachments

Tool to list all add-on attachments created under an announcement.

Delete Add-on Attachment

Tool to delete an add-on attachment from course work.

Get Add-on Context for Course Work

Tool to get metadata for Classroom add-ons in the context of a specific course work.

List Add-on Attachments on Course Work Material

Tool to list all add-on attachments under a course work material post.

Delete Course Work Material

Tool to delete a course work material.

Modify CourseWork Assignees

Tool to modify assignee mode and options of coursework.

Patch Course Work

Tool to update one or more fields of a course work.

List Course Work Rubrics

Tool to list rubrics for a specific coursework.

Create Course

Tool to create a new course.

Delete Course

Tool to delete a course.

Get Course

Tool to get details for a specific course.

Get Grading Period Settings

Tool to retrieve grading period settings for a course.

List Courses

Tool to list all courses accessible to the authenticated user.

Patch Course

Tool to update one or more fields of a Classroom course.

List Post Add-on Attachments

Tool to list all add-on attachments created under a post.

Get Add-on Context for Post

Tool to get metadata for Classroom add-ons in the context of a specific post.

Add Student to Course

Tool to add a student to a course.

Delete Course Student

Tool to delete a student from a course.

Get Course Student

Tool to retrieve a specific student of a course.

List Student Guardians

Tool to list guardians of a student in a course.

List Course Students

Tool to list students in a course.

Delete Course Teacher

Tool to delete a teacher from a course.

Get Teacher

Tool to get teacher enrollment.

List Course Teachers

Tool to list teachers in a course.

Create Course Topic

Tool to create a course topic.

Delete Course Topic

Tool to delete a course topic.

Get Course Topic

Tool to get a course topic.

List Course Topics

Tool to list topics in a course.

Patch Course Topic

Tool to update fields of a course topic.

Update Course

Tool to update a course.

Patch Course Work Material

Tool to update fields of a course work material.

Create CourseWork

Tool to create a CourseWork item in a course.

Delete CourseWork

Tool to delete a specific CourseWork.

Get CourseWork

Tool to get details of a specific coursework.

List CourseWork

Tool to list coursework in a course.

Create Course Work Material

Tool to create course work material.

Get Coursework Material

Tool to get a coursework material.

List CourseWorkMaterials

Tool to list course work materials in a course.

List Student Submissions

Tool to list student submissions for a specific coursework.

Reclaim Student Submission

Tool to reclaim a student submission for editing.

Get CourseWork Add-on Attachment

Tool to get an add-on attachment from course work.

Get Add-on Context for Course Work Material

Tool to get metadata for Classroom add-ons in the context of a specific course work material.

Create Invitation

Tool to create an invitation for a user to a course.

Delete Invitation

Tool to delete an invitation.

Get Invitation

Tool to retrieve an invitation by its identifier.

List Invitations

Tool to list invitations that the requesting user is permitted to view.

List Course Student Groups

Tool to list student groups in a course.

List CourseWork Add-on Attachments

Tool to list all add-on attachments created by an add-on under a course work.

Create Registration

Tool to create a registration for push notifications from Google Classroom.

Get User Profile

Tool to retrieve a user profile by user ID.

FAQ

Frequently asked questions

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

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

Start with Google Classroom.It takes 30 seconds.

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

Start building