imscc-mcp
An MCP server that enables the creation of Canvas Common Cartridge (.imscc) packages from structured course data using the canvas_cc Ruby gem. It allows users to programmatically build course content including modules, assignments, and rubrics for import into compatible Learning Management Systems.
README
imscc-mcp
Repo: https://github.com/InquiryInstitute/imscc_mcp
MCP server that builds Canvas Common Cartridge (.imscc) packages using Instructure’s Ruby gem canvas_cc. Cartridges are Canvas-profile CC files; many LMSes (including Populi) can import valid Common Cartridge 1.x zip/imscc.
Populi: “webcontent … skipped”
Wiki/lesson pages from canvas_cc are type="webcontent" in imsmanifest.xml. Populi often skips them (you may see two errors for two pages). Assignments typically use associatedcontent/imscc_xmlv1p1/learning-application-resource and import more reliably. When authoring from imscc_template, run assemble-spec.mjs --populi to omit wiki pages and wiki module items; see docs/POPULI.md there.
Prerequisites
- Node.js ≥ 18
- Ruby + Bundler
- From this repo root:
bundle install(installs gems intovendor/bundleper.bundle/config)
Setup
cd ~/GitHub/imscc_mcp
bundle install
npm install
npm run build
Tests
bundle install
npm install
npm test
Runs integration checks on ruby/build_cartridge.rb: successful builds produce a ZIP with imsmanifest.xml; invalid specs are rejected.
Run
node dist/index.js
Cursor / MCP client
Point command at node and args at the absolute path to dist/index.js after npm run build. No env vars are required.
Tools
| Tool | Purpose |
|---|---|
imscc_build_cartridge |
Build .imscc from structured input (course, pages, modules, assignments, …). |
imscc_example_spec |
Minimal JSON example for imscc_build_cartridge. |
imscc_check_environment |
Check ruby, bundle, and canvas_cc from this repo. |
imscc_canvas_cc_reference |
Links to canvas_cc, Populi CC import, 1EdTech. |
Spec notes
output_directory: absolute path; created if missing.course.title: required.- Assignments — Supported: groups, points,
submission_types(e.g.online_text_entry,online_upload), due dates, HTML body. Link a rubric withrubric_identifier(must match arubrics[].identifier), plus optionalrubric_use_for_grading/rubric_hide_score_total. - Rubrics —
rubrics[]withidentifier,external_identifier(defaults toidentifier),title, optionalpoints_possible, andcriteria[]each withid,description,points, andratings[](id,description,points,criterion_idmatching the criterionid). - Slides / decks — There is no separate “slides” type. Package files (e.g.
.pptx,.pdf) underfiles[]withidentifier,file_path(path inside the course files tree), andfile_location(absolute path on the machine that runs the build). Optionally add a module item withcontent_typeAttachmentandidentifierrefset to the file’sidentifier(see canvas_cc module item types). - Module items — e.g.
WikiPage+identifierrefmatching a pageidentifier, orExternalUrl+url. - Assignments → groups —
assignment_group_identifier_refmust match an assignment groupidentifier.
Importer support (Canvas vs Populi vs others) varies; test imports on your LMS.
For types not yet mapped in ruby/build_cartridge.rb (quizzes, question banks, full LTI, etc.), extend the script using the canvas_cc README.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.