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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。