🎓 Canvas LMS MCP Server

A robust Model Context Protocol (MCP) server that connects Claude AI to your Canvas LMS account — letting you interact with your coursework using natural language.

Built with Python · Canvas REST API · MCP SDK

✨ Features (14 Tools across 4 Modules)

📚 Assignments & Courses

📊 Grades

📢 Announcements & Modules

📅 Calendar

Related MCP server: Canvas LMS MCP Server

🚀 Setup

1. Clone the repo

git clone https://github.com/adityas0604/MCP-Canvas.git
cd canvas-mcp

2. Install dependencies

pip install -r requirements.txt

How to get your Canvas API Token:

1. Log into Canvas

2. Go to Account → Settings

3. Scroll to Approved Integrations

4. Click New Access Token

5. Copy and save this token.

3. Configure Claude Desktop

Add this to your claude_desktop_config.json:

Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "canvas": {
      "command": "python",
      "args": ["/absolute/path/to/canvas-mcp/server.py"],
      "env": {
        "CANVAS_BASE_URL": "canvas_base_url"
        "CANVAS_API_TOKEN": "your_token_here"
      }
    }
  }
}

4. Restart Claude Desktop

The Canvas tools will now appear in your Claude sidebar!

💬 Example Prompts

Once connected, try asking Claude:

• "What assignments do I have due this week?"

• "What's my current GPA estimate?"

• "Am I missing any assignments?"

• "What announcements have my professors posted recently?"

• "Show me my grade breakdown for course 12345"

• "What does my week look like?"

🔒 Privacy & Security

• Read-only — this server never writes, submits, or modifies your Canvas data

🛠️ Tech Stack

• Python 3.10+

• MCP SDK — Model Context Protocol

• httpx — Async-ready HTTP client

• python-dotenv — Environment config

• Canvas LMS REST API