Skip to content
agentusehub

Manage Canvas courses in plain English

The author built a Canvas LMS tool with Claude Code that lets educators list courses, find missing submissions, monitor forums, schedule announcements and export the gradebook.

Time saved
Not reported
Setup time
Not reported
Running cost
Not reported
Cost range
Not reported

Use case overview

The author built a Canvas LMS tool with Claude Code that lets educators list courses, find missing submissions, monitor forums, schedule announcements and export the gradebook.

Reported experience

  1. What they did

    A non-developer educator used Claude Code over four months to build an MCP server in Python on FastMCP, starting from a 200-line proof of concept that listed courses. It grew into modular tools covering assignments, discussions, announcements and gradebook export, with API tokens kept in environment variables. Claude Code did the refactoring and API handling. A colleague contributed group-management features.

  2. How it went

    The author says a 45-minute weekly check of submissions and participation became a 2-minute conversation. The codebase reached about 3,000 lines. Source-level anonymization of student data was added later; early screenshots predate it.

  3. Worth knowing

    Setup is said to take about 15 minutes, but you need Canvas API permissions. Start with simple queries like listing courses before trying analytics.

Example prompts

Try with Claude Code
Build me a small tool that connects to [LMS, e.g. Canvas] using my API token stored in [environment variable] so I can manage my courses in plain English. It should be able to list my courses, find students with missing submissions in [course], and export the gradebook to CSV. Test it with read-only actions first, and before it schedules or posts any announcement, show me the text and ask for my confirmation.
Software & DevOps

Port a Chrome extension to Safari

The author had ChatGPT take the Session Buddy extension source from Chrome, port it to Safari and install it, taking about 20 minutes.

ChatGPT