canvas mcp
A set of tools enabling AI agents to interact with Canvas LMS, allowing users to find relevant resources, get course information, and navigate modules through natural language queries.
A set of tools enabling AI agents to interact with Canvas LMS, allowing users to find relevant resources, get course information, and navigate modules through natural language queries.
Canvas MCP is a set of tools that allows your AI agents to interact with Canvas LMS and Gradescope.
Note down the following beforehand:
1. Canvas API Key from Canvas > Account > Settings > Approved Integrations > New Access Token
2. Gemini API key from https://aistudio.google.com/app/apikey
3. Gradescope Email and Password https://www.gradescope.com/
To install Canvas MCP for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @aryankeluskar/canvas-mcp --client claude
Or, for Cursor IDE to use canvas-mcp with 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
Download the repository and run the following commands:
git clone https://github.com/aryankeluskar/canvas-mcp.git
cd canvas-mcp
# Install dependencies with uv (recommended)
pip install uv
uv venv
source .venv/bin/activate # On Windows: .venvScriptsactivate
uv pip install -r requirements.txt
# Or install with pip
pip install -r requirements.txt
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 to your mcp.json
or claude_desktop_config.json
file:
{
"mcpServers": {
"canvas": {
"command": "uv",
"args": [
"--directory",
"/Users/aryank/Developer/canvas-mcp",
"run",
"canvas.py"
]
}
}
}
Built by Aryan Keluskar :)