BYU Learning Suite MCP Server
Enables Claude Desktop to interact with BYU Learning Suite data including assignments, grades, schedule, announcements, exams, and course content, currently using mock data.
README
BYU Learning Suite MCP Server
A local MCP server that exposes BYU Learning Suite data (assignments, grades, schedule, announcements, exams, and course content) as tools for Claude Desktop.
Currently uses mock data for a BYU junior Finance student (Spring 2026). The data layer is modular — swap mockAdapter.js for a real scraper without changing any MCP logic.
Setup
cd byu-learning-suite-mcp
npm install
Run Standalone (for testing)
npm start
The server communicates over stdio, so you won't see output — it's waiting for MCP messages.
Connect to Claude Desktop
Add the following to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"byu-learning-suite": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/byu-learning-suite-mcp/src/index.js"]
}
}
}
Replace the path with your actual absolute path, then restart Claude Desktop.
Available Tools
| Tool | Description | Params |
|---|---|---|
get_assignments |
Upcoming assignments | course?, days_ahead? (default 14) |
get_grades |
Grade summary (or drill into one course) | course? |
get_schedule |
Weekly class schedule | — |
get_announcements |
Recent announcements | course?, limit? (default 10) |
get_exams |
Upcoming exams & testing center windows | course? |
get_content |
Course content & resources | course? |
Architecture
src/
├── index.js # MCP server entry point
├── tools/
│ └── index.js # Tool definitions (MCP schema + handlers)
└── data/
├── adapter.js # Adapter interface (dependency injection point)
├── mockAdapter.js # Mock implementation (filters/sorts mock data)
└── mockData.js # Raw mock data (courses, assignments, grades, etc.)
Swapping to a Real Backend
- Create
src/data/scraperAdapter.jsexporting an object with the same interface asmockDataSource(each method is async and returns the expected shape). - In
src/index.js, import your scraper and pass it tocreateAdapter():
import { scraperDataSource } from "./data/scraperAdapter.js";
const data = createAdapter(scraperDataSource);
That's it — the tools and MCP server remain unchanged.
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。