Canvas MCP Server

A Model Context Protocol server providing comprehensive access to Canvas LMS for AI assistants.

Access Canvas LMS functionality through 31 MCP tools:

• Courses: List and view course information
• Assignments: Browse, view details, check submissions, and submit work
• Grades: View grades for individual courses or across all courses
• Messaging: Send and receive messages, manage conversations (read/unread, star, archive, delete)
• Calendar: View events and upcoming deadlines
• To-Do Lists: Track pending tasks and assignments
• Modules: Navigate course content structure
• Announcements: Read course and institutional announcements
• Files: Access and download course materials
• Quizzes: View quizzes and submissions
• Users: Search for classmates and instructors

• Bun runtime
• Canvas LMS account with API access token

1. Install dependencies:

bun install

2. Get your Canvas API token:

   • Log into Canvas
   • Navigate to Account → Settings
   • Scroll to "Approved Integrations"
   • Click "+ New Access Token"
   • Generate and copy the token

3. Configure environment variables:

export CANVAS_BASE_URL="https://your-institution.instructure.com"
export CANVAS_ACCESS_TOKEN="your_access_token_here"

4. Configure your MCP client with the following settings:

{
  "mcpServers": {
    "canvas": {
      "command": "bun",
      "args": ["run", "/absolute/path/to/canvas/src/index.ts"],
      "env": {
        "CANVAS_BASE_URL": "https://your-institution.instructure.com",
        "CANVAS_ACCESS_TOKEN": "your_access_token_here"
      }
    }
  }
}

After setup, interact with Canvas through your MCP client:

Show me all my current courses
What assignments do I have due soon?
What are my grades in all my classes?
Show me my recent Canvas messages

bun run format      # Format code with Prettier
bun run lint        # Lint code with ESLint
bun run typecheck   # Type check with TypeScript
bun test            # Run tests

bun run build       # Build for production
bun run dev         # Run in development mode

• Quick Start Guide
• Usage Examples
• Tool Reference
• Changelog

Built with TypeScript and the MCP SDK, this server provides a type-safe interface to the Canvas LMS REST API. All operations use Bearer token authentication and respect Canvas rate limits.

canvas/
├── src/
│   ├── canvas/
│   │   ├── client.ts        # Canvas API client
│   │   └── client.test.ts   # Client tests
│   └── index.ts             # MCP server implementation
├── docs/                    # Documentation
├── package.json             # Dependencies and scripts
└── tsconfig.json           # TypeScript configuration

• Store credentials in environment variables
• Never commit access tokens to version control
• Use token expiration dates
• Rotate tokens regularly
• Follow your institution's API usage policies

This server implements the Canvas LMS REST API v1. For detailed API documentation, visit the Instructure Developer Portal.

This project uses permissive open-source dependencies with no telemetry or tracking.