How to Use the D2L Brightspace MCP in LangChain

Q: How do I connect D2L Brightspace to LangChain?

Install langchain-mcp-adapters and langgraph. Initialize a MultiServerMCPClient pointing to your Vinkius MCP endpoint. Fetch the tools with client.gettools() and pass them to your ReAct agent.

Q: Can LangChain agents grade D2L Brightspace assignments?

Yes. Your pipeline can pull documents using listsubmissions, evaluate them against a rubric, and push scores back via updateusergrade. LangSmith logs the entire evaluation path.

Q: How do I handle persistent context across sessions?

The client runs stateless by default. Call client.session() to keep track of course IDs and user contexts between operations. This prevents the agent from repeating expensive API lookups.

Build multi-step ReAct agents that read assignments, grade quizzes, and manage enrollments in D2L Brightspace using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect D2L Brightspace MCP to LangChain

Create your Vinkius account to connect D2L Brightspace to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup D2L Brightspace with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain D2L Brightspace data into LangChain pipelines

`get_course` and `list_org_unit_children` pull raw structural data straight from your LMS. You feed that output directly into a ReAct agent. The chain decides which child units need updates before triggering the next step. Observability matters when you hit external APIs. LangSmith traces every token sent to the Brightspace MCP server. You see exactly what context your agent used before calling `create_course`.

Automate grading and feedback loops

`list_submissions` and `get_user_grade` grab student work from specific assignment folders. Your pipeline reads the submission text, runs it through a custom grading rubric step, and generates a score. The final node in your MCP chain applies the result. Writing that data back requires precision. Your agent calls `update_user_grade` and `provide_feedback` to push the final evaluation into the gradebook. No manual data entry required.

Provision users and LTI tools dynamically

`create_user` and `create_enrollment` handle the identity side of your LMS. Your agent parses an incoming CSV of new hires or students, checks existing records, and provisions accounts. It assigns roles on the fly based on the input data. Technical integrations get the same treatment via this MCP Server. `create_lti_deployment` registers third-party learning tools across specific org units. You build chains that configure external apps without clicking through the admin dashboard.

Setup guide

Set up D2L Brightspace MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes D2L Brightspace tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "d2l-brightspace-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent D2L Brightspace transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by D2L Brightspace. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect D2L Brightspace now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about D2L Brightspace MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph`. Initialize a `MultiServerMCPClient` pointing to your Vinkius MCP endpoint. Fetch the tools with `client.get_tools()` and pass them to your ReAct agent.

Yes. Your pipeline can pull documents using `list_submissions`, evaluate them against a rubric, and push scores back via `update_user_grade`. LangSmith logs the entire evaluation path.

Tracing works out of the box. LangSmith captures latency, input arguments, and raw outputs for every tool executed. You know exactly why an agent created a specific user.

The client runs stateless by default. Call `client.session()` to keep track of course IDs and user contexts between operations. This prevents the agent from repeating expensive API lookups.

The tools access student grades, quiz attempts, and user profile information. Vinkius isolates this traffic in an ephemeral V8 sandbox. Zero data persists after the connection closes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript