Canvas LMS MCP Server

The TypeScript MCP server for Canvas LMS.

MCP server for Canvas LMS. Read courses, assignments, submissions, rubrics, quizzes; grade, comment, manage course content, and handle Canvas admin workflows from any AI agent.

104 tools across Canvas courses, assignments, submissions, gradebook history, rubrics, quizzes, files, users, groups, enrollments, discussions, modules, pages, calendar, conversations, peer reviews, accounts, analytics, outcomes, student workflows, dashboard, and health checks. Three deployment modes: stdio, HTTP, and library import.

Comparison

	canvas-lms-mcp	vishalsachdev/canvas-mcp	DMontgomery40/mcp-canvas-lms
Language	TypeScript	Python	TypeScript
Tools	104	80+	54
License
Last commit

Quick Start

1. Get a Canvas API Token

1. Log in to your Canvas instance
2. Go to Account > Settings
3. Scroll to Approved Integrations and click + New Access Token
4. Give it a name (e.g., "MCP Server") and click Generate Token
5. Copy the token immediately -- you won't see it again

2. One Command Setup

npx add-mcp canvas-lms-mcp

This auto-detects your installed AI clients (Claude Code, Cursor, VS Code, etc.) and configures them. You will be prompted for your Canvas API token and base URL.

Client-Specific Commands

Claude Code

claude mcp add canvas-lms --env CANVAS_API_TOKEN=your-token --env CANVAS_BASE_URL=https://school.instructure.com -- npx -y canvas-lms-mcp

VS Code

code --add-mcp '{"name":"canvas-lms","command":"npx","args":["-y","canvas-lms-mcp"],"env":{"CANVAS_API_TOKEN":"your-token","CANVAS_BASE_URL":"https://school.instructure.com"}}'

Gemini CLI

gemini mcp add canvas-lms npx canvas-lms-mcp

Codex CLI

codex mcp add canvas-lms -- npx canvas-lms-mcp

{
  "mcpServers": {
    "canvas-lms": {
      "command": "npx",
      "args": ["-y", "canvas-lms-mcp"],
      "env": {
        "CANVAS_API_TOKEN": "your-token-here",
        "CANVAS_BASE_URL": "https://your-institution.instructure.com"
      }
    }
  }
}

{
  "mcpServers": {
    "canvas-lms": {
      "command": "npx",
      "args": ["-y", "canvas-lms-mcp"],
      "env": {
        "CANVAS_API_TOKEN": "your-token-here",
        "CANVAS_BASE_URL": "https://your-institution.instructure.com"
      }
    }
  }
}

{
  "mcp.servers": {
    "canvas-lms": {
      "command": "npx",
      "args": ["-y", "canvas-lms-mcp"],
      "env": {
        "CANVAS_API_TOKEN": "your-token-here",
        "CANVAS_BASE_URL": "https://your-institution.instructure.com"
      }
    }
  }
}

{
  "mcpServers": {
    "canvas-lms": {
      "command": "npx",
      "args": ["-y", "canvas-lms-mcp"],
      "env": {
        "CANVAS_API_TOKEN": "your-token-here",
        "CANVAS_BASE_URL": "https://your-institution.instructure.com"
      }
    }
  }
}

npx canvas-lms-mcp serve --port 3001 \
  --token your-token-here \
  --base-url https://your-institution.instructure.com

Example Prompts

Once configured, try these prompts with your AI client:

• "List all my active courses"
• "Show me the assignments for course 12345"
• "What's the average grade on the midterm exam?"
• "Grade Alice's essay submission with a B+ and add feedback"
• "Show me the rubric for the final project"
• "What discussions are happening in my Biology course?"
• "List all upcoming calendar events for course 12345"
• "Send a message to student 67890 about their missing assignment"

Tool Inventory

All Registered Tools (104)

76 tools are read-only and 28 tools perform Canvas write operations.

All write tools require appropriate Canvas permissions. Canvas enforces its own permission model -- the MCP server does not bypass it.

MCP Resources (2)

Deployment Modes

stdio (Default)

For local AI clients like Claude Desktop, Cursor, and VS Code. The server communicates over stdin/stdout.

npx canvas-lms-mcp --token $CANVAS_API_TOKEN --base-url $CANVAS_BASE_URL

HTTP

For web-based clients or hosted services. Starts an HTTP server with Streamable HTTP transport.

npx canvas-lms-mcp serve \
  --token $CANVAS_API_TOKEN \
  --base-url $CANVAS_BASE_URL \
  --port 3001 \
  --allowed-origin https://your-app.example.com

Endpoints:

• POST /mcp -- MCP protocol endpoint
• GET /health -- Health check (returns {"status":"ok"})

Docker

docker compose up -d

Requires CANVAS_API_TOKEN and CANVAS_BASE_URL environment variables. See docker-compose.yml.

services:
  canvas-lms-mcp:
    build: .
    ports:
      - "3001:3001"
    environment:
      - CANVAS_API_TOKEN=${CANVAS_API_TOKEN}
      - CANVAS_BASE_URL=${CANVAS_BASE_URL}

Library Import

Use the server factory directly in your own Node.js application:

import { createCanvasMCPServer } from 'canvas-lms-mcp'

const { server, canvas } = createCanvasMCPServer({
  token: userToken,
  baseUrl: canvasBaseUrl,
})

Or use the Canvas client standalone (no MCP dependency):

import { CanvasClient } from 'canvas-lms-mcp/canvas'

const canvas = new CanvasClient({
  token: userToken,
  baseUrl: canvasBaseUrl,
})

const courses = await canvas.courses.list()

CLI Reference

Environment Variables

Development

pnpm install       # Install dependencies
pnpm dev           # Watch mode build
pnpm build         # Production build
pnpm test          # Run tests (294 tests)
pnpm lint          # ESLint + Prettier check
pnpm lint:fix      # Auto-fix lint issues
pnpm typecheck     # TypeScript strict type check

Dependency audit

The pnpm.overrides.hono entry pins hono to 4.12.14 because @modelcontextprotocol/sdk@1.29.0 allows vulnerable hono <4.12.14 versions. Remove the override when the MCP SDK publishes a release that depends on a patched hono range.

Architecture

src/canvas/       Standalone Canvas REST API client (pure fetch, no MCP dependency)
src/tools/        MCP tool definitions with Zod input schemas
src/resources/    MCP resource templates (syllabus, assignment description)
src/server.ts     Factory: createCanvasMCPServer(config)
src/stdio.ts      stdio transport entry point
src/http.ts       HTTP transport entry point
src/cli.ts        CLI argument parser

Contributing

See CONTRIBUTING.md for the full contribution and validation workflow.

1. Fork the repo
2. Create a feature branch (git checkout -b feat/my-feature)
3. Use conventional commits (feat:, fix:, chore:, test:, docs:)
4. Ensure pnpm lint && pnpm typecheck && pnpm test pass
5. Open a pull request

Guides

• Getting Started -- Step-by-step setup for non-developers: token, config, first query, troubleshooting
• Student Guide -- Token setup, AI client configuration, 10 example prompts
• Educator Guide -- Grading workflows, write operations, privacy considerations
• Integration Guide -- Three integration patterns with code examples
• Agent Discovery -- Generated tool/workflow manifests and workflow-pack index
• Educator Assignment Review Workflow -- Read-first grading flow with write-safety guidance
• Student Weekly Planning Workflow -- Read-only weekly planning sequence for students

License

MIT