Canvas MCP Connector
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CANVAS_BASE_URL | Yes | The base URL of your Canvas LMS instance (e.g., https://canvas.example.edu) | |
| CANVAS_ACCESS_TOKEN | Yes | Your Canvas access token |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| canvas_list_coursesA | List the authenticated user's active Canvas courses. |
| canvas_get_upcomingA | Get upcoming events and assignment deadlines for the authenticated user. |
| canvas_list_assignmentsC | List assignments for one Canvas course. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool targets a distinct facet: courses, upcoming deadlines, and per-course assignments. canvas_get_upcoming and canvas_list_assignments could both surface due dates, but their global-versus-course-specific scope keeps them distinguishable.
All tools share a canvas_ prefix and use snake_case. The only minor inconsistency is mixing list (canvas_list_courses, canvas_list_assignments) with get (canvas_get_upcoming), but the pattern remains predictable.
Three tools is on the small side, but each tool covers a core read-only Canvas workflow without redundancy. It is slightly thin for a full-fledged connector, but reasonable for a simple course/deadline dashboard.
The set supports listing courses, listing assignments, and viewing upcoming deadlines, which covers a basic student-facing workflow. However, it lacks deeper Canvas operations such as course detail lookups, assignment details, grades, submissions, or any lifecycle actions.