How to integrate D2lbrightspace MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
D2lbrightspace Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting D2lbrightspace to AutoGen 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quiz for my math course, add a new user to the spring semester, copy an instructor role for a new department, delete an outdated course template from the system through natural language commands.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 AutoGen 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:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for D2lbrightspace
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call D2lbrightspace tools
  • Run a live chat loop where you ask the agent to perform D2lbrightspace operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A D2lbrightspace account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

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 dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to D2lbrightspace via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's D2lbrightspace connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a D2lbrightspace session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["d2lbrightspace"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes D2lbrightspace tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create D2lbrightspace assistant agent with MCP tools
    agent = AssistantAgent(
        name="d2lbrightspace_assistant",
        description="An AI assistant that helps with D2lbrightspace operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the D2lbrightspace tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any D2lbrightspace related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which D2lbrightspace tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with D2lbrightspace and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a D2lbrightspace session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["d2lbrightspace"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create D2lbrightspace assistant agent with MCP tools
        agent = AssistantAgent(
            name="d2lbrightspace_assistant",
            description="An AI assistant that helps with D2lbrightspace operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any D2lbrightspace related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into D2lbrightspace through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for D2lbrightspace, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

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

Vercel AI SDK

Vercel AI SDK

Use D2lbrightspace MCP with Vercel AI SDK

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 Autogen?

Yes, you can. Autogen 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