canvas-mcp-tool

---

Leverage on to quickly scan through your courses, find assignments and related content & stay up to date with your academics.

📋 Available Tools

• list_assignments - List assignments for a course
• get_assignment - Get assignment details
• list_courses - List your enrolled courses
• get_course - Get details about a specific course
• get_profile - Get your user profile
• list_users - List users in a course
• get_dashboard_cards - Get your dashboard cards
• list_calendar_events - List calendar events
• get_file_metadata - Get information about a Canvas file
• get_file_content - Extract text content from Canvas files (DOCX, TXT, and more)

Claude Desktop

{
  "mcpServers": {
    "canvas": {
      "command": "npx",
      "args": ["-y", "canvas-mcp-tool"],
      "env": {
        "CANVAS_API_URL": "https://your-schools-canvas-url.com",
        "CANVAS_API_TOKEN": "your_token_here",
        "CANVAS_API_VERSION": "v1",
        "CANVAS_API_TIMEOUT": "30000",
        "CANVAS_MAX_RETRIES": "3"
      }
    }
  }
}

Claude Code (Recommended)

# Simple usage (if env vars are already set in your shell):
claude mcp add canvas -- npx -y canvas-mcp-tool

# Or inline specify all required and optional variables:
CANVAS_API_URL="https://your-schools-canvas-url.com" \
CANVAS_API_TOKEN="your_canvas_api_token_here" \
CANVAS_API_VERSION="v1" \
CANVAS_API_TIMEOUT=30000 \
CANVAS_MAX_RETRIES=3 \
claude mcp add canvas -- npx -y canvas-mcp-tool

Gemini CLI

Add to your ~/.gemini/settings.json:

{
  "mcpServers": {
    "canvas": {
      "command": "npx",
      "args": ["-y", "canvas-mcp-tool"],
      "env": {
        "CANVAS_API_URL": "https://your-schools-canvas-url.com",
        "CANVAS_API_TOKEN": "your_token_here",
        "CANVAS_API_VERSION": "v1",
        "CANVAS_API_TIMEOUT": "30000",
        "CANVAS_MAX_RETRIES": "3"
      }
    }
  }
}

Note: Gemini CLI requires all environment variables to be explicitly defined in the configuration.

Configuration

After installation, you'll need to configure your Canvas URL and API token:

Getting a Canvas API Token

Warning: Your Canvas API token is sensitive - treat it like a password and never share it or commit it to source control.

1. Log into your Canvas account
2. Go to Account → Settings
3. Scroll to "Approved Integrations"
4. Click "+ New Access Token"
5. Enter a purpose and click "Generate Token"
6. Copy the token and use in it your preferred setup.

For Claude Desktop

You can add these to your shell profile (~/.zshrc, ~/.bashrc, etc.) so they're loaded automatically:

# ~/.zshrc or ~/.bashrc
export CANVAS_API_URL="https://your-schools-canvas-url.com"
export CANVAS_API_TOKEN="your_canvas_api_token_here"
export CANVAS_API_VERSION="v1"
export CANVAS_API_TIMEOUT=30000
export CANVAS_MAX_RETRIES=3

Local Setup

1. Clone this repository

2. Install dependencies:

   npm install

3. Create a .env file with your Canvas credentials:

   cp .env.example .env

4. Edit .env and add your Canvas API token:

   CANVAS_API_URL=https://your-schools-canvas-url.com
   CANVAS_API_TOKEN=your_canvas_api_token_here
   

   Add optional cache and logging settings (defaults shown):

   CACHE_ENABLED=true          # Enable response caching (set to false to disable)
   CACHE_TTL=300               # Cache time-to-live in seconds
   LOG_LEVEL=info              # Logging level: debug, info, warn, error
   LOGGING_ENABLED=true        # Enable logging (set to false to disable)
   

Build

npm run build

---

🛈 What is an MCP?