Canvas Learning Management System

🚀 Canvas MCP Server

This repository contains an implementation of the Message Control Protocol (MCP) server that interfaces with the Canvas Learning Management System (LMS) API. The server is designed to be used with Claude Desktop and other potential MCP clients.

🚀 Quick Start

The Canvas MCP server offers a local interface to access the Canvas LMS API, enabling you to:

• List and manage courses
• Access assignments and submissions
• View announcements
• Obtain course outlines and modules
• Manage users and enrollment information
• Generate course summaries

✨ Features

Prerequisites

• Python 3.x
• Virtual environment (venv)
• Canvas API token
• Canvas API URL (e.g., https://canvas.illinois.edu/api/v1)

📦 Installation

Clone the Repository

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

Create and Activate the Virtual Environment

python -m venv canvas-mcp
source canvas-mcp/bin/activate  # On Unix/macOS

Install Dependencies

pip install -r requirements.txt

📚 Documentation

Configuration

Create an Environment File

Create a .env file in the root directory with the following variables:

CANVAS_API_TOKEN=your_canvas_api_token_here
CANVAS_API_URL=https://canvas.youruniversity.edu/api/v1

Replace with your actual values:

• Your Canvas API token (How to get your Canvas API token)
• The Canvas API URL of your institution

Configure the Startup Script

The start_canvas_server.sh script is already configured to:

• Load environment variables from the .env file
• Activate the virtual environment
• Run the cache server implementation

Mark the startup script as executable:

chmod +x start_canvas_server.sh

Configure Claude Desktop

1. Download and install Claude Desktop if not already installed.
2. Open the Claude app and navigate to Settings.
3. Select Environment Variables in the left sidebar.
4. Add the following variables:
   • Name: CANVAS_API_TOKEN Value: Your Canvas API token
   • Name: CANVAS_API_URL Value: The Canvas API URL of your institution

Install the MCP Server

1. Open a terminal and navigate to the canvas-mcp directory.
2. Run the installation command:

pip install .

Using the Server

Start the MCP server:

python -m canvas_mcp.server

Security Considerations

• Your Canvas API token grants access to your Canvas account.
• Never commit the .env file to version control.
• Consider using tokens with restricted permissions if possible.
• The server runs on your local machine and does not expose your credentials externally.

Contributing

Contributions are welcome! Feel free to:

• Submit issues to report bugs or request features.
• Create pull requests to improve the project.
• Share your use cases and feedback.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Created by Vishal Sachdev