canvas-mcp

Canvas MCP for Students

Welcome! This guide will help you set up Canvas MCP to use Claude as your personal Canvas assistant.

What Can Canvas MCP Do for You?

Think of this as having an AI study buddy that knows everything about your Canvas courses:

Prerequisites

Installation

1. Clone the Repository

git clone https://github.com/vishalsachdev/canvas-mcp.git
cd canvas-mcp

2. Install Dependencies

# Install uv package manager (faster than pip)
pip install uv

# Install Canvas MCP
uv pip install -e .

3. Get Your Canvas API Token

  1. Log in to your Canvas account
  2. Go to AccountSettings
  3. Scroll down to Approved Integrations
  4. Click + New Access Token
  5. Give it a purpose (e.g., “Claude AI Assistant”)
  6. Click Generate Token
  7. Copy the token immediately - you won’t see it again!

4. Configure Canvas MCP

Create a .env file in the canvas-mcp directory:

# Copy the template
cp env.template .env

# Edit the .env file and add your credentials

Your .env file should look like this:

# Canvas API Configuration
CANVAS_API_TOKEN=your_token_here
CANVAS_API_URL=https://canvas.youruniversity.edu/api/v1

# MCP Server Configuration (optional)
MCP_SERVER_NAME=canvas-mcp

# Privacy Settings (students don't need anonymization)
ENABLE_DATA_ANONYMIZATION=false

Important: Replace https://canvas.youruniversity.edu/api/v1 with your actual Canvas URL (including the /api/v1 suffix).

5. Configure Claude Desktop

Add Canvas MCP to Claude Desktop’s configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "canvas-api": {
      "command": "canvas-mcp-server"
    }
  }
}

6. Test Your Setup

# Test the Canvas API connection
canvas-mcp-server --test

You should see: ✓ API connection successful!

7. Restart Claude Desktop

Close and reopen Claude Desktop. You should see the 🔨 hammer icon when you start a conversation.

How to Use Canvas MCP

Quick Start Prompts

Try these with Claude:

Assignment Tracking:

Grade Monitoring:

Submission Status:

Peer Reviews:

Course Content:

Discussions:

Understanding Tool Calls

When you ask Claude a question, you’ll see it use various “tools” (indicated by the 🔨 icon). These tools fetch data from Canvas. For example:

Available Student Tools

Personal Organization

Academic Performance

Peer Review Management

Course Content (Shared Tools)

Privacy & Security

Your Data Stays Private

Best Practices

Troubleshooting

“Connection failed” or “Authentication error”

“No tools appearing in Claude”

“No assignments/courses showing up”

Need More Help?

Example Workflows

Morning Check-In

You: "Good morning! What do I need to focus on today?"

Claude will:
1. Check your upcoming assignments (next 24-48 hours)
2. Show any incomplete peer reviews
3. List recent announcements
4. Highlight your TODO items

Weekly Planning

You: "Help me plan my week"

Claude will:
1. Show all assignments due in the next 7 days
2. Identify which courses need attention
3. Check peer review deadlines
4. Summarize your current grade status

Before a Big Assignment

You: "I have a paper due Friday in ENGL 101. What do I need to know?"

Claude will:
1. Find the assignment details
2. Check if you've submitted
3. Show the rubric (if available)
4. Review peer review requirements (if applicable)

Tips for Best Results

  1. Be specific about courses: Use course codes (e.g., “BADM 350”) when you can
  2. Ask follow-up questions: Claude remembers context within a conversation
  3. Request summaries: “Summarize my workload for next week”
  4. Combine requests: “Show me my grades and what’s due this week”

What’s Next?

Now that you’re set up, explore what Canvas MCP can do! Try different prompts and see how Claude can help streamline your academic workflow.

Happy studying! 📚