Compatible with every major AI agent and IDE
What is the D2L Brightspace MCP Server?
Connect your D2L Brightspace environment to any AI agent to streamline learning management and administrative workflows.
What you can do
- Course Management — Retrieve course details, create new offerings, and copy course content between org units using
get_courseandcopy_course. - User Administration — List system users, create new accounts, and manage roles and permissions with
list_usersandcreate_user. - Grade Tracking — Access grade lists and update individual student grades for specific assignments using
get_user_gradeandupdate_user_grade. - Content & Communication — Explore course modules, manage discussion forums, and create new topics or posts via
list_root_modulesandcreate_post. - Assessments — Monitor quizzes, surveys, and assignment submissions, and provide direct feedback using
list_submissionsandprovide_feedback.
How it works
- Subscribe to this server
- Provide your Brightspace Host URL and Access Token
- Start managing your educational ecosystem from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Instructors — Quickly check student progress, provide feedback on assignments, and manage course content without navigating complex menus.
- LMS Administrators — Automate user creation, enrollment management, and organizational unit structuring.
- Academic Researchers — Extract course data and assessment metrics for analysis through natural language queries.
Built-in capabilities (33)
Initiate a course copy job
Create a course offering
Enroll a user in an org unit
Create an LTI Advantage tool deployment
Create custom org units
Create a post in a discussion topic
Create a discussion topic in a forum
Create a new user
Unenroll a user from an org unit
Retrieve course details
Retrieve course template info
Retrieve org unit properties
Retrieve user grades for a specific grade object
Retrieve current user context
List assignment folders (dropboxes)
List discussion forums in a course
List grade objects for a course
List legacy LTI 1.1 links
List LTI Advantage tool registrations
List current user enrollments
List current user ePortfolio objects
List child units of an org unit
List attempts for a specific quiz
List quizzes in a course
Retrieve system roles
List root modules of course materials
List submissions for an assignment folder
List surveys in a course
Search or page through users
Provide feedback for an assignment submission
Update user data
Update a user grade
Upload a file artifact to ePortfolio
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 33 tools from D2L Brightspace through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries D2L Brightspace, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
D2L Brightspace in OpenAI Agents SDK
D2L Brightspace and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect D2L Brightspace to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for D2L Brightspace in OpenAI Agents SDK
The D2L Brightspace MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 33 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
D2L Brightspace for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the D2L Brightspace MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check a specific student's grade for a course unit?
Yes. By using the get_user_grade tool with the appropriate Org Unit ID and User ID, the agent can retrieve the current grade details for that student.
Is it possible to list all modules within a course structure?
Absolutely. Use the list_root_modules tool to fetch the top-level content structure for any specific course org unit.
Can I manage discussion forums through this agent?
Yes, you can use list_forums to see available forums and create_topic or create_post to interact with the discussion boards.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Unleash (Feature Toggles)
11 toolsManage feature flags, strategies, and environments via Unleash — evaluate toggles, list projects, and monitor metrics directly from your AI agent.

Lemlist
8 toolsEquip your AI agent with direct access to Lemlist — manage cold email campaigns, track lead engagement, and automate outreach without opening the Lemlist dashboard.

PCA Dimensionality Engine
1 toolsPerform native Principal Component Analysis to safely reduce high-dimensional datasets without losing critical variance.

Crawlbase
10 toolsScrape and crawl via Crawlbase — perform HTML extraction, handle JS-rendered pages, bypass CAPTCHAs, and scrape social profiles directly from any AI agent.
