How to integrate Google Classroom MCP with Vercel AI SDK v6

This guide walks you through connecting Google Classroom to Vercel AI SDK v6 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 Vercel AI 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.

Get started for freeGet a demo
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 Vercel AI SDK v6 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 Vercel AI 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

ChatGPTOpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenCodeCursorVS CodeOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Google Classroom integration
  • Using Composio's Tool Router to dynamically load and access Google Classroom 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 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 you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
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
  • 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.
3

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
4

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
5

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
6

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: ["google_classroom"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Google Classroom 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 Google Classroom-related tools through the MCP protocol
7

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 Google Classroom tools that the agent can use
8

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 google_classroom, 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
9

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 Google Classroom 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 Google Classroom 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: ["google_classroom"],
  });

  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 google_classroom, 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 Google Classroom 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.
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.

FRAMEWORKS

How to build Google Classroom MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Google Classroom MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Google Classroom MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Google Classroom MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Google Classroom MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Google Classroom MCP with Claude Cowork

Codex logo

Codex

Use Google Classroom MCP with Codex

Cursor logo

Cursor

Use Google Classroom MCP with Cursor

OpenClaw logo

OpenClaw

Use Google Classroom MCP with OpenClaw

Hermes logo

Hermes

Use Google Classroom MCP with Hermes

CLI logo

CLI

Use Google Classroom MCP with CLI

Google ADK logo

Google ADK

Use Google Classroom MCP with Google ADK

LangChain logo

LangChain

Use Google Classroom MCP with LangChain

Mastra AI logo

Mastra AI

Use Google Classroom MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Google Classroom MCP with LlamaIndex

CrewAI logo

CrewAI

Use Google Classroom MCP with CrewAI

OpenCode logo

OpenCode

Use Google Classroom MCP with OpenCode

VS Code logo

VS Code

Use Google Classroom MCP with VS Code

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. 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 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
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies