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


Features
- Find relevant resources - Ability to find relevant resources for a given query in natural language!
- Query upcoming assignments - Not only fetch upcoming assignments, but also provide its breakdown for a given course.
- Get courses and assignments from Gradescope - Query your Gradescope courses and assignments with natural language, get submission status, and more!
- Get courses
- Get modules
- Get module items
- Get file url
- Get calendar events
- Get assignments
- and so much more…
Usage
Note down the following beforehand:
- Canvas API Key from
Canvas > Account > Settings > Approved Integrations > New Access Token - Gemini API key from https://aistudio.google.com/app/apikey
- Gradescope Email and Password https://www.gradescope.com/
Installing via Smithery (Preferred)
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
Manual Installation (ONLY for local instances)
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
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 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 :)
Canvas Integration Server
Project Details
- jpablomm/mcp-hackathon-canvas
- MIT License
- Last Updated: 5/2/2025
Recomended MCP Servers
A simple POC to expose Mythic as a MCP server
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and...
MCP server for Directus API integration
Korean to Chinese translator built as an MCP tool using DeepSeek LLM
A Model Context Protocol (MCP) server that interfaces with Taiwan's Central Weather Administration (CWA) API.
A Model Context Protocol Server connector for Bitrefill public API, to enable AI agents to search and shop...
FEGIS is a framework for structured cognition and persistent memory in language models using Anthropic's Model Context Protocol....
无需服务器,一键部署,快速使用自建节点分享URL进行订阅转换,提供灵活的自定义选项,支持SingBox/Clash/V2Ray/Xray





