From your university account
to the AI tools you use.
Course materials should remain available when you start a new AI conversation. UnivMCP is being designed to collect your authorized university resources locally, synchronize them to the cloud, and let connected AI applications retrieve them when needed.
This page describes the system we are building. The first target is Chung-Ang University e-Class on macOS.
- 01 / SOURCEUniversity LMSYour courses and their original resources.
- 02 / ON YOUR DEVICELocal CollectorUniversity authentication, resource collection, and outbound sync.
- 03 / SYNCHRONIZEDUnivMCP CloudCourse metadata, original files, and access for your paired AI connection.
- 04 / WHEN NEEDEDMCP / API → AIConnected tools retrieve your synchronized course context.
Connect locally. Retrieve remotely.
Your university credentials stay on your device.
The local collector handles university sign-in. Persistent secrets are intended to use macOS Keychain-backed storage. Cloud synchronization uses a separate device identity.
Your course materials travel with their context.
The first storage contract includes original files and normalized metadata. Source course and resource identifiers keep each file tied to the right academic context.
Access follows your university account.
The collector observes resources available to your account. The cloud associates those observations with your paired identity, so the AI-facing interface can retrieve your synchronized resources.
Synchronization happens in the background.
Planned triggers include app startup, device wake, periodic collection while the device is active, and a manual refresh. AI reads the last synchronized state, with sync status available alongside it.
The AI application reads from UnivMCP Cloud. It does not need an inbound connection to your laptop to retrieve resources that have already synchronized.
A shared interface for course context.
MCP stands for Model Context Protocol. It gives compatible AI applications a standard way to connect to tools and resources. UnivMCP’s planned remote MCP and API surface will let connected tools list courses, find materials, retrieve a resource, and check synchronization status.
University-specific authentication belongs in the local adapter. The AI interface works with normalized cloud state, allowing the same learning context to serve additional compatible clients.
Chung-Ang e-Class → macOS → AI.
The first milestone is a daily-usable flow from local collection through cloud synchronization to remote resource retrieval. Course resources come first; assignments, announcements, additional university adapters, and other desktop platforms can follow as the core path matures.
Where the project began
The maintainer currently uses cau-eclass-mcp with Codex. This early CAU integration provides practical experience with LMS behavior and real course resources. UnivMCP builds on those lessons with a broader local collector, cloud sync, and remote retrieval design.