Niches · Learning, tutoring & assessment

Build or change course content for a teacher

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

0companies, full fit
2companies, fit with a limit
5companies carry the tag
21share of the category's work
8first-hand accounts

What counts as done

The course items created or changed through the API precisely as asked, with nothing else in the course altered or removed, and the change visible in the course system afterwards.

How agents ask for it: create groups from this spreadsheet, add a rubric to the essay assignment, rename week 3 and add the reading, set up next term's course shell

Does the job, with a limit 2

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Instructure Canvas C
Instructure, Inc.
Assignments, Groups, Group Categories and Rubrics have create endpoints, but acc-14 saw a rubric edit create a new rubric and lose the original, there is no sandbox, and unapproved MCP servers are barred. source
Moodle BB
Moodle Pty Ltd
core_course_create_courses, core_group_create_groups, core_course_edit_section and core_courseformat_update_course exist, but acc-27 saw a section rename wipe its description and acc-31 tests writes only on a sandbox. source

Doesn't do this job 4

Listings in the category that do something else, with the reason.

ListingWhy
Kahoot! C
Kahoot! AS
No write endpoints; course or kahoot changes stay in the app. source
Learnosity C
Learnosity Limited
Learnosity holds items and activities embedded in another product, not courses, groups, sections or rubrics on assignments. source
Preply C
Preply, Inc.
No course or content endpoints. source
Quizgecko F
Version Zero Limited
Quizgecko builds its own study courses; it does not create or change items in a teacher's course system. source

What stops agents finishing

  • update endpoint replaces the object, wiping fields not sent
  • no create endpoint for the object (groups, rubric edits) in the connector or API
  • no sandbox, so writes are tested on live courses

Around it

Before: spreadsheets.read-table, document-extraction.pdf-to-text. After: messaging.announce.

Where this comes from

Weight 21 of 100 in Learning, tutoring & assessment: 8 of 32 accounts; instructors and tool builders on Canvas and Moodle MCP servers, half of them reporting writes that did more or less than asked

The same as data: /api/v1/use-cases/learning.course-authoring.json, or the MCP tool get_use_case with id learning.course-authoring. Other jobs in this category: /api/v1/niches?category=learning.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.