Skip to main content
Glama

Canvas MCP

Read-only FastMCP server for Canvas LMS study data.

This project is configured for CIAM Canvas by default:

https://ciam.instructure.com

Configuration

Set these environment variables before starting the server:

export CANVAS_BASE_URL="https://ciam.instructure.com"
export CANVAS_API_TOKEN="your-canvas-token"

Do not commit real Canvas tokens.

Related MCP server: canvas-lms

Install

cd /Users/zihanwang/Documents/Codex/canvas-mcp
uv sync --extra dev

Run

cd /Users/zihanwang/Documents/Codex/canvas-mcp
uv run canvas-mcp

The server speaks MCP over stdio.

MCP Client Config

Use this shape in an MCP client config. Replace your-canvas-token with your token in your local config only.

{
  "mcpServers": {
    "canvas": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/zihanwang/Documents/Codex/canvas-mcp",
        "run",
        "canvas-mcp"
      ],
      "env": {
        "CANVAS_BASE_URL": "https://ciam.instructure.com",
        "CANVAS_API_TOKEN": "your-canvas-token"
      }
    }
  }
}

Tools

  • canvas_self: current Canvas user.

  • canvas_courses: visible courses, defaulting to active enrollments.

  • canvas_course_assignments: assignments for a course.

  • canvas_upcoming_events: upcoming calendar events.

  • canvas_todo: todo items for the current user.

  • canvas_course_modules: modules and module items for a course.

  • canvas_course_pages: wiki pages for a course, with optional search.

  • canvas_course_files: files for a course, with optional folder filtering.

  • canvas_submissions: assignment submissions or visible course submissions.

  • canvas_raw_get: read-only escape hatch for /api/v1/... Canvas paths.

Local Verification

cd /Users/zihanwang/Documents/Codex/canvas-mcp
uv run pytest -v
uv run python -c "from canvas_mcp.server import mcp; print(mcp.name)"

Expected output from the smoke test:

Canvas LMS

Live API Smoke Test

After setting CANVAS_API_TOKEN, this should return your Canvas user profile:

cd /Users/zihanwang/Documents/Codex/canvas-mcp
uv run python - <<'PY'
from canvas_mcp.client import CanvasClient, CanvasConfig

client = CanvasClient(CanvasConfig.from_env())
try:
    print(client.get("users/self", paginate=False))
finally:
    client.close()
PY

Available Tools

10 tools
canvas_course_assignmentsC

List assignments for a Canvas course.

Inputs: course_id (required), include_submissions.

canvas_course_filesB

List files for a Canvas course, optionally scoped to a folder.

Inputs: course_id (required), folder_id.

canvas_course_modulesC

List modules and module items for a Canvas course.

Inputs: course_id (required).

canvas_course_pagesB

List wiki pages for a Canvas course.

Inputs: course_id (required), search_term.

canvas_coursesC

List Canvas courses visible to the configured token.

Inputs: enrollment_state.

canvas_raw_getC

Run a read-only GET against a Canvas /api/v1/... path.

Inputs: path (required), paginate.

canvas_selfA

Return the current Canvas user for the configured token.

Inputs: no named parameters.

canvas_submissionsC

List submissions for an assignment or visible course submissions.

Inputs: course_id (required), assignment_id.

canvas_todoA

List Canvas todo items for the current user.

Inputs: no named parameters.

canvas_upcoming_eventsC

List upcoming Canvas calendar events.

Inputs: days.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct Canvas resource (courses, assignments, files, modules, pages, user info, submissions, todo, events, raw API access) with no overlap in purpose, making selection unambiguous for an agent.

    Naming Consistency5/5

    All tools follow a consistent 'canvas_<resource>' snake_case pattern, using descriptive nouns. Even 'canvas_raw_get' and 'canvas_self' fit the pattern, with no mixing of conventions.

    Tool Count5/5

    10 tools is well within the ideal range (3-15). The set covers common Canvas read operations without being excessive or insufficient for its scope.

    Completeness4/5

    The set provides comprehensive read coverage for Canvas (courses, assignments, files, modules, pages, submissions, todo, events) and includes a raw GET endpoint for flexibility. However, it lacks write operations (create, update, delete), which are absent from the tool descriptions.

    Related MCP Connectors

    Related MCP Servers