Canvas Academic Assistant 🎓

An AI-powered academic management tool that connects your Canvas LMS with Claude Desktop. Ask Claude natural questions about your coursework, assignments, grades, and deadlines - all through conversational AI.

🌟 What This Does

This tool transforms Claude into your personal academic assistant by connecting it directly to your Canvas account. Instead of logging into Canvas and clicking through multiple pages, you can simply ask Claude:

• "What assignments do I have due this week?"
• "Show me my current grades in all courses"
• "What announcements did I miss?"
• "What's on my Canvas calendar for tomorrow?"
• "Help me prioritize my upcoming deadlines"

✨ Features

📚 Course Management

• View all your active courses
• Get course details and enrollment information

📝 Assignment Tracking

• See upcoming assignments and deadlines
• Get detailed assignment information
• Check your to-do list items

📊 Grade Monitoring

• View grades across all courses
• Check assignment submission status
• Track your academic progress

📅 Calendar Integration

• Access your Canvas calendar events
• See upcoming due dates and deadlines

📢 Stay Updated

• Get course announcements
• View recent Canvas activity
• Never miss important updates

🚀 Quick Start Guide

Prerequisites

You'll need:

• A Canvas account (this was built for Carnegie Mellon University but works with any Canvas instance)
• Claude Desktop installed on your computer
• Python 3.10 or newer

Step 1: Get Your Canvas API Token

1. Log into Canvas at your school's Canvas website
2. Click "Account" in the left sidebar
3. Go to "Settings"
4. Scroll down to "Approved Integrations"
5. Click "+ New Access Token"
6. Enter a purpose like "Claude Academic Assistant"
7. Copy the generated token (you won't see it again!)

Step 2: Download and Set Up

1. Download this project to your computer
2. Open Terminal (Mac) or Command Prompt (Windows)
3. Navigate to the project folder:

   cd path/to/canvas-mcp-server

Step 3: Install Dependencies

1. Create a virtual environment:

   python3 -m venv venv

2. Activate it:

   • Mac/Linux: source venv/bin/activate
   • Windows: venv\Scripts\activate

3. Install required packages:

   pip install mcp httpx python-dotenv pydantic

Step 4: Configure Your Token

1. Open the .env file in the project folder
2. Replace the token with yours:

   CANVAS_API_TOKEN=your_token_here
   CANVAS_BASE_URL=https://your-school.instructure.com
   

Step 5: Test the Setup

Run this command to make sure everything works:

python src/canvas_server.py

You should see:

✅ Canvas API connection successful
🚀 Canvas MCP Server started

Press Ctrl+C to stop the test.

Step 6: Connect to Claude Desktop

1. Find your Claude Desktop configuration file:

   • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json

2. Add this configuration (replace the path with your actual project location):

{
  "mcpServers": {
    "Canvas Academic Assistant": {
      "command": "/path/to/your/canvas-mcp-server/venv/bin/python",
      "args": [
        "/path/to/your/canvas-mcp-server/src/canvas_server.py"
      ],
      "env": {
        "CANVAS_API_TOKEN": "your_token_here"
      },
      "enabled": true,
      "autostart": true
    }
  }
}

3. Restart Claude Desktop completely (quit and reopen)

🎯 How to Use

Once set up, you can ask Claude natural questions about your academic life:

📋 Assignment Management

• "What assignments are due this week?"
• "Show me details about my math homework"
• "What's the next deadline I need to worry about?"
• "Help me prioritize my upcoming assignments"

📊 Grade Tracking

• "What are my current grades?"
• "How am I doing in Computer Science?"
• "Show me my grade for the last assignment"

📅 Schedule Planning

• "What's on my calendar tomorrow?"
• "When is my next exam?"
• "What Canvas events do I have this week?"

📢 Staying Updated

• "Any new announcements in my courses?"
• "What Canvas activity did I miss?"
• "Show me recent updates from professors"

🤖 AI-Powered Help

• "Help me create a study schedule based on my deadlines"
• "What should I focus on today?"
• "Remind me about upcoming important dates"

🔧 Troubleshooting

❌ "Could not connect to MCP server"

• Make sure Python path in your config is correct
• Check that your virtual environment is set up properly
• Verify your Canvas token is still valid

❌ "Canvas API connection failed"

• Double-check your Canvas token in the .env file
• Make sure your Canvas URL is correct
• Verify you're connected to the internet

❌ "No data returned"

• Ensure you're enrolled in active courses
• Check that your Canvas account has proper permissions
• Try regenerating your Canvas API token

🆘 Need Help?

1. Check that all file paths in your configuration are absolute paths
2. Make sure your Canvas token hasn't expired
3. Restart Claude Desktop after any configuration changes
4. Test the server manually first using Step 5 above

🎓 Built For Students

This tool was originally created for Carnegie Mellon University students but works with any Canvas installation. It's designed to help students:

• Save time by getting information through conversation instead of clicking through Canvas
• Stay organized with AI-powered deadline management
• Never miss important announcements or due dates
• Focus on learning instead of administrative tasks

🔒 Privacy & Security

• Your Canvas token stays on your computer - nothing is sent to external servers
• All communication happens locally between Claude Desktop and your Canvas instance
• Your academic data remains private and secure

📚 What You Can Access

The tool provides access to the same information you can see in Canvas:

• Your enrolled courses
• Assignment details and due dates
• Your grades and submissions
• Course announcements
• Calendar events
• Recent activity

Note: You can only access your own data - the same permissions apply as when using Canvas directly.

---

Ready to transform your academic workflow? Set it up in 10 minutes and start having conversations with Claude about your coursework! 🚀