Compatible with every major AI agent and IDE
What is the Canvas LMS MCP Server?
Connect your Canvas LMS instance to any AI agent to automate course administration and student management through natural conversation.
What you can do
- Course Management — List, create, update, or delete courses. Fetch detailed metadata for specific course IDs.
- Account Administration — Navigate account hierarchies, list sub-accounts, and update organizational details.
- User Operations — Create and update user profiles, or retrieve specific user details and activity streams.
- Assignments & Tasks — List all assignments within a course and track your personal 'To Do' items and activity stream.
- Workflow Automation — Use your AI as a teaching assistant or admin to handle repetitive setup tasks in the LMS.
How it works
- Subscribe to this server
- Enter your Canvas Domain (e.g., school.instructure.com) and Personal Access Token
- Start managing your virtual classroom from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Educators & Tutors — quickly check assignment lists or update course details without navigating complex menus
- LMS Administrators — automate user creation and account management across sub-accounts
- Students & Developers — track personal todos and activity streams directly from the terminal or code editor
Built-in capabilities (45)
Make a user an admin in an account
Create a new assignment in a course
Create a new conversation
Create a new Canvas course
Create a new discussion topic in a course
Create a new quiz in a course
Create a new role in an account
Import SIS data
Create a new Canvas user
Delete or conclude a Canvas course
Execute a GraphQL query against Canvas
Get details for a specific Canvas account
Get current user activity stream
Get details for a specific assignment
Get details for a specific conversation
Get details for a specific Canvas course
Get details for a specific file
Get details for a specific folder
Get details for a specific page
Get details for a specific quiz
Get status of a SIS import
Get sub-accounts for a specific account
Get current user todo items
Show user details
Grade a submission
List Canvas accounts
List admins in an account
List announcements
List assignments for a course
List conversations (Inbox)
List your Canvas courses
List discussion topics in a course
List files in a course
List sub-folders within a folder
List items in a specific module
List modules in a course
List pages in a course
List quizzes in a course
List roles in an account
List submissions for an assignment
Submit an assignment
Update an existing Canvas account
Edit an existing assignment
Update an existing Canvas course
Update an existing Canvas user
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 45 tools from Canvas LMS through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Canvas LMS, 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
Canvas LMS in OpenAI Agents SDK
Canvas LMS and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Canvas LMS 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 Canvas LMS in OpenAI Agents SDK
The Canvas LMS 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 45 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
Canvas LMS for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Canvas LMS MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I see my personal upcoming tasks and deadlines?
Yes! Use the get_todo tool to retrieve your current todo items or get_activity_stream to see recent updates and announcements across your courses.
How do I list all assignments for a specific course?
Simply provide the Course ID to the list_assignments tool. The agent will return a list of all assignments configured for that specific course environment.
Is it possible to create or update courses through this integration?
Yes. You can use create_course to instantiate new courses under an account, or update_course to modify names and codes of existing ones.
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 →
Thoughtly
11 toolsDeploy AI voice agents to make or receive calls, manage CRM contacts, and access call histories instantly.

NeonCRM
10 toolsManage non-profit operations via NeonCRM — track donations, memberships, and events directly from your AI agent.

Trimble
10 toolsEquip your AI agent with enterprise-grade truck routing, commercial geocoding, and advanced toll cost logistics algorithms.

Payrexx
11 toolsAccept payments online with a Swiss payment gateway that supports local and international methods with PCI compliance built in.
