Skip to main content
Glama

Canvas MCP Server

A Model Context Protocol (MCP) server implementation for the Canvas LMS API. This server provides functionality to interact with Canvas LMS programmatically.

Features

  • List courses from Canvas LMS with optional enrollment type filtering

  • Interactive help prompts for using the tools

Related MCP server: canvas-mcp

Prerequisites

  • Node.js 18 or later

  • A Canvas LMS instance

  • Canvas API access token

  • Cursor (for client integration)

Setup

  1. Clone this repository

  2. Install dependencies:

    npm install
  3. Set up environment variables:

    export CANVAS_BASE_URL="https://your-canvas-instance.com"
    export CANVAS_ACCESS_TOKEN="your-api-token"
  4. Build the project:

    npm run build
  5. Start the server:

    npm start

Connecting with Cursor

To use this MCP server with Cursor:

  1. Open Cursor's settings

  2. Navigate to the MCP configuration section

  3. Add a new server configuration:

    {
      "mcpServers": {
        "canvas": {
          "command": "npm",
          "args": [
            "start"
          ],
          "cwd": "/path/to/mcp-server-canvas"
        }
      }
    }
  4. Save the configuration and restart Cursor

  5. The Canvas tools will now be available in Cursor's MCP tools panel

Available Tools

list_courses

Lists all courses from Canvas LMS.

Parameters:

  • enrollment_type (optional): Filter courses by enrollment type (teacher, student, ta)

Example response:

{
  "content": [
    {
      "type": "text",
      "text": [
        {
          "id": 1234,
          "name": "Example Course",
          "code": "EX101",
          "state": "available",
          "startDate": "2024-01-01T00:00:00Z",
          "endDate": "2024-12-31T23:59:59Z"
        }
      ]
    }
  ]
}

list-courses-help

An interactive prompt that provides help with using the list_courses tool.

Development

The server is built using TypeScript and the MCP SDK. To add new features:

  1. Add new API methods to the CanvasAPI class

  2. Register new tools using server.tool()

  3. Register help prompts using server.prompt()

  4. Build and test your changes

Troubleshooting

If you encounter issues:

  1. Check that environment variables are set correctly

  2. Verify your Canvas API token has the necessary permissions

  3. Check Cursor's MCP server logs for any error messages

  4. Ensure the server path in Cursor's configuration is correct

License

MIT

Available Tools

1 tool
get_user_coursesC

Get courses for a specific user with optional grading count

Inputs: user_id (required), include_grading_count, enrollment_state.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of confusion or overlap between tools. The tool has a clear, specific purpose focused on retrieving user courses, leaving no ambiguity for an agent to misselect.

    Naming Consistency5/5

    The single tool name follows a consistent verb_noun pattern (get_user_courses), making it predictable and readable. There are no other tools to compare against, so no inconsistency can arise.

    Tool Count2/5

    One tool is too few for a server named 'Canvas MCP Server', which suggests a broader educational platform scope (e.g., courses, assignments, grades). This minimal set severely limits functionality and feels incomplete for the implied domain.

    Completeness1/5

    The tool surface is severely incomplete for a Canvas server, covering only user course retrieval. There are obvious gaps: no CRUD operations for courses, assignments, submissions, or grades, and no ability to create, update, or delete resources, which will cause significant agent failures.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      C
      quality
      C
      maintenance
      Local-first MCP server for Canvas LMS. Stdio transport, no third-party broker, token stays in ~/.canvas.env. Exposes courses, assignments, modules, announcements, grades, planner items, upcoming events, todo list, and bulk file dump as MCP tools.
      10
      49 PyPI
      4
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables students, instructors, and account administrators to interact with Canvas LMS through natural language, covering course and module navigation, assignment submission and grading, quizzes, discussions, announcements, grades, files, and account-level user, course, and reporting administration. It supports both stdio and streamable HTTP transports with automatic retries, pagination, and a broad set of Canvas API tools.
      21 npm
      MIT