loaditout.ai
SkillsPacksTrendingLeaderboardAPI DocsBlogSubmitRequestsCompareAgentsXPrivacyDisclaimer
{}loaditout.ai
Skills & MCPPacksBlog

canvas-mcp

MCP Tool

aryankeluskar/canvas-mcp

Collection of Canvas LMS and Gradescope tools for the model context protocol. Query your courses, find resources, and chat with your upcoming assignments.

Install

$ npx loaditout add aryankeluskar/canvas-mcp

Platform-specific configuration:

.claude/settings.json
{
  "mcpServers": {
    "canvas-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "canvas-mcp"
      ]
    }
  }
}

Add the config above to .claude/settings.json under the mcpServers key.

About

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:

  1. Canvas API Key from Canvas > Account > Settings > Approved Integrations > New Access Token
  2. Gradescope Email and Password https://www.gradescope.com/
Installing via Smithery (Preferred)

To install Canvas MCP for Claude Code via Smithery:

npx -y @smithery/cli@latest mcp add aryankeluskar/canvas-mcp --client claude-code

Or, for Cursor IDE to use canvas-mcp with other models:

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

Or, for ChatGPT:

  1. Enable Developer Mode in settings, if not already enabled
  2. Go to ChatGPT Settings > Connectors and click Create to add this server URL: https://canvas-mcp--aryankeluskar.run.tools

---

Manual Configuration (ONLY for local instances)

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

SNITHERY_API_KEY=your_snithery_api_key

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

{
  "mcpServers": {
      "canvas": {
          "command": "npx",
          "args": [
              "-y",
              "@smithery/cli",
              "run",
              "@aryankeluskar/canvas-mcp"
    

Tags

anthropicbuncanvasmcptypescriptsmithery

Reviews

Loading reviews...

Quality Signals

11
Stars
0
Installs
Last updated38 days ago
Security: AREADME
New

Safety

Risk Levelmedium
Data Access
read
Network Accessnone

Details

Sourcesmithery
Last commit3/11/2026
View on GitHub→

Embed Badge

[![Loaditout](https://loaditout.ai/api/badge/aryankeluskar/canvas-mcp)](https://loaditout.ai/skills/aryankeluskar/canvas-mcp)