Canvas LMS

🚀 Canvas MCP Teacher Edition

Canvas MCP is a set of tools that allows your AI agents to interact with Canvas LMS and Gradescope.

✨ Features

• Find relevant resources - It can find relevant resources when using natural language queries!
• Query upcoming assignments - Not only can it retrieve upcoming assignments, but it can also provide breakdown information for a given course.
• Get courses and assignments from Gradescope - Use natural language to query Gradescope courses and assignments, obtain information such as submission status, and learn more!
• Get courses
• Get modules
• Get module items
• Get file links
• Get calendar events
• Get assignments
• And more...

🚀 Quick Start

Record the following information in advance:

1. Obtain the Canvas API key from Canvas > Account > Settings > Approved Integrations > New Access Token.
2. Gemini API key https://aistudio.google.com/app/apikey.
3. Gradescope email and password https://www.gradescope.com/.

📦 Installation via Smithery (Recommended)

To automatically install Canvas MCP via Smithery for use on Claude Desktop:

npx -y @smithery/cli install @aryankeluskar/canvas-mcp --client claude

Alternatively, for using canvas - mcp with Cursor IDE and other models:

npx -y @smithery/cli install @aryankeluskar/canvas-mcp --client cursor

Or, for Windsurf:

npx -y @smithery/cli install @aryankeluskar/canvas-mcp --client windsurf

📦 Manual Installation (Local Instance Only)

Download the repository and run the following commands:

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

# Install dependencies using uv (Recommended)
pip install uv
uv venv
source .venv/bin/activate  # For Windows: .venv\Scripts\activate
uv pip install -r requirements.txt

# Or install using pip
pip install -r requirements.txt

Manual Configuration

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

CANVAS_API_KEY=your_canvas_api_key
GEMINI_API_KEY=your_gemini_api_key

Add the following content to your mcp.json or claude_desktop_config.json file:

{
  "mcpServers": {
      "canvas": {
          "command": "uv",
          "args": [
              "--directory",
              "/Users/aryank/Developer/canvas-mcp",
              "run",
              "canvas.py"
          ]
      }
  }
}

Developed by Aryan Keluskar!