How to integrate D2lbrightspace MCP with Vercel AI SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
D2lbrightspace Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting D2lbrightspace to Vercel AI SDK using the Composio tool router. By the end, you'll have a working D2lbrightspace agent that can create a new quiz for my math course, add a new user to the spring semester, copy an instructor role for a new department, delete an outdated course template from the system through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a D2lbrightspace account through Composio's D2lbrightspace 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:
  • How to set up and configure a Vercel AI SDK agent with D2lbrightspace integration
  • Using Composio's Tool Router to dynamically load and access D2lbrightspace 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
  • Step Counting: Control multi-step tool execution
  • OpenAI Provider: Native integration with OpenAI models

What is the D2lbrightspace MCP server, and what's possible with it?

The D2lbrightspace MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your D2L Brightspace account. It provides structured and secure access to your LMS, so your agent can perform actions like creating courses, managing quizzes, handling user enrollment, and automating gradebook operations on your behalf.

  • Automated course creation and management: Instantly create new courses, course offerings, or templates, and streamline updates or deletions without manual intervention.
  • Quiz and assessment automation: Let your agent set up new quizzes, organize quiz categories, and configure assessment parameters to enhance the learning experience.
  • Gradebook and feedback management: Effortlessly create, modify, or delete grade objects to keep your course grading up to date and provide prompt feedback to learners.
  • User enrollment and management: Create new user accounts, manage user roles, and handle enrollment or impersonation tasks to simplify onboarding and administration.
  • Role and permissions control: Copy existing roles, adjust specific permissions, and fine-tune access for different user groups—all directly through your agent.

Supported Tools & Triggers

Tools
Copy RoleCreates a new role copied from an existing role in d2l brightspace.
Create Course OfferingCreates a new course offering in d2l brightspace.
Create Course TemplateCreates a new course template in d2l brightspace.
Create Grade ObjectCreates a new grade object for a particular org unit.
Create QuizCreates a new quiz in d2l brightspace.
Create Quiz CategoryCreates a new quiz category in d2l brightspace.
Create UserCreates a new user entity in d2l brightspace.
Delete Course TemplateDeletes a course template from d2l brightspace.
Delete CourseDeletes a course offering from d2l brightspace.
Delete Grade ObjectDeletes a specific grade object from an org unit.
Delete QuizDeletes a quiz from d2l brightspace.
Delete Quiz CategoryDeletes a quiz category from d2l brightspace.
Delete UserDeletes a user entity from d2l brightspace.
Delete User DemographicsDeletes one or more of a particular user's associated demographics entries.
Get Course OfferingRetrieves a specific course offering from d2l brightspace.
Get Course TemplateRetrieves a course template from d2l brightspace.
Get Course SchemaRetrieves the list of parent org unit type constraints for course offerings.
Get Course Template SchemaRetrieves the list of parent org unit type constraints for course offerings built on this template.
Get Current User InformationRetrieves the current user context's user information from d2l brightspace.
Get Enrolled RolesRetrieves a list of all enrolled user roles the calling user can view in an org unit.
Get Grade AccessRetrieves a list of users with access to a specified grade.
Get Grade ObjectRetrieves a specific grade object for a particular org unit.
Get Grade ObjectsRetrieves all current grade objects for a particular org unit.
Get Grade SetupRetrieves the grades configuration for an org unit.
Get Grade StatisticsRetrieves statistics for a specified grade item.
Get Org Unit DemographicsRetrieves all demographics entries for users enrolled in a particular org unit.
Get QuizRetrieves a specific quiz from an org unit.
Get Quiz AccessRetrieves a list of users with access to a specified quiz.
Get Quiz AttemptRetrieves a specific quiz attempt.
Get Quiz AttemptsRetrieves a list of attempts for a quiz.
Get Quiz CategoriesRetrieves all quiz categories belonging to an org unit.
Get Quiz CategoryRetrieves a specific quiz category from an org unit.
Get Quiz QuestionsRetrieves all questions in a quiz.
Get QuizzesRetrieves all quizzes belonging to an org unit.
Get Role by IDRetrieves a particular user role from d2l brightspace by its id.
Get RolesRetrieves a list of all known user roles in d2l brightspace.
Get User by IDRetrieves data for a particular user from d2l brightspace.
Get UsersRetrieves data for one or more users from d2l brightspace.
Update Course OfferingUpdates an existing course offering in d2l brightspace.
Update Course TemplateUpdates an existing course template in d2l brightspace.
Update Grade ObjectUpdates a specific grade object.
Update Grade SetupUpdates the grades configuration for an org unit.
Update QuizUpdates an existing quiz in d2l brightspace.
Update Quiz CategoryUpdates an existing quiz category in d2l brightspace.
Update UserUpdates an existing user entity in d2l brightspace.

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 you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

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.

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

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

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 { experimental_createMCPClient as 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

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: ["d2lbrightspace"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to D2lbrightspace 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 D2lbrightspace-related tools through the MCP protocol

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 D2lbrightspace tools that the agent can use

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 d2lbrightspace, 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

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 D2lbrightspace 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 D2lbrightspace 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 { experimental_createMCPClient as 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: ["d2lbrightspace"],
  });

  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 d2lbrightspace, 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 D2lbrightspace 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.

How to build D2lbrightspace MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use D2lbrightspace MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use D2lbrightspace MCP with Claude Agent SDK

Google ADK

Google ADK

Use D2lbrightspace MCP with Google ADK

LangChain

LangChain

Use D2lbrightspace MCP with LangChain

Mastra AI

Mastra AI

Use D2lbrightspace MCP with Mastra AI

LlamaIndex

LlamaIndex

Use D2lbrightspace MCP with LlamaIndex

CrewAI

CrewAI

Use D2lbrightspace MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and D2lbrightspace MCP?

With a standalone D2lbrightspace MCP server, the agents and LLMs can only access a fixed set of D2lbrightspace tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from D2lbrightspace and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Vercel AI SDK?

Yes, you can. Vercel AI 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 D2lbrightspace tools.

Can I manage the permissions and scopes for D2lbrightspace while using Tool Router?

Yes, absolutely. You can configure which D2lbrightspace 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 D2lbrightspace 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.

Book a call↗Get started for free