Advertise
MCP.so
Sign In

Canvas MCP Server

@avarant

Repository

Basic information

Category

Other

License

MIT license

Transports

stdio

Author

avarant

About Canvas MCP Server

an mcp server for interacting with canvas

Canvas MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "canvas-mcp-server": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "-r",
        "requirements.txt",
        "#",
        "Assuming",
        "a",
        "requirements.txt",
        "might",
        "be",
        "added",
        "later"
      ]
    }
  }
}

Canvas MCP Server tools

5

Fetches the list of active courses for the current user.

Fetches the list of assignments for a specific course ID.

Fetches calendar events (assignments) for specified context codes (defaults to user).

Fetches upcoming calendar events (including assignments) for the user.

Fetches detailed information for a specific course ID.

Overview

What is Canvas MCP Server?

A Canvas Model Context Protocol (MCP) server implemented in Python that exposes Canvas API functionalities as MCP tools using the canvas-lms-sdk. It is intended for users who want to programmatically interact with their Canvas LMS instance via MCP-compatible clients.

How to use Canvas MCP Server?

Set the CANVAS_API_URL and CANVAS_API_KEY environment variables with your Canvas credentials, install dependencies using uv (or pip) from the required repositories, then run python main.py. The server will start and listen for MCP client connections.

Key features of Canvas MCP Server?

  • Fetches active courses for the current user
  • Retrieves assignments for a specific course ID
  • Checks calendar due dates for specified context codes
  • Lists upcoming calendar events and assignments
  • Returns detailed information for a given course ID

Use cases of Canvas MCP Server?

  • Get an overview of all currently active courses
  • View assignments and due dates for a specific course
  • Check upcoming assignment deadlines on a calendar
  • Access detailed course information (e.g., syllabus, settings)
  • Automate Canvas data retrieval through MCP workflows

Frequently asked questions

1

What are the prerequisites for running the server?

Python 3.8 or later, the `uv` package manager (or `pip`), and a Canvas API URL and API key from your institution.

2

How do I set up environment variables?

Export `CANVAS_API_URL` (e.g., `https://<your-institution>.instructure.com`) and `CANVAS_API_KEY` before running the server. For production, use a secure secret manager.

3

Which dependencies need to be installed?

The server requires `canvas-lms-sdk` (installed from a GitHub repository) and `mcp-sdk`. Install them via `uv pip install` or `pip` as shown in the README.

4

How do I start the server?

After setting environment variables and installing dependencies, run `python main.py` from the project directory.

5

What tools does the server currently provide?

Five tools: `get_active_courses`, `get_assignments_for_course`, `get_calendar_due_dates`, `get_upcoming_assignments`, and `get_class_information`.

Comments

More Other MCP servers

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Advertise