XCS221 Course Guide MCP Server
Helps AI agents answer XCS221 course logistics questions (e.g., deadlines, pacing, repositories) from static in-repo data without external APIs.
README
XCS221 MCP Server Template
Template MCP server that helps AI agents answer common XCS221 course logistics questions from static in-repo data (no auth, no external APIs).
What this template answers
Out of the box, it is designed for questions such as:
- When are assignments due?
- Where should I be in lectures/assignments today?
- Which git repository has setup or assignment code?
The server exposes both direct tools and a natural-language router tool.
Tech stack
- Language: TypeScript (Node.js)
- MCP SDK:
@modelcontextprotocol/sdk - Validation:
zod - Tests:
vitest
TypeScript is a strong fit because the official MCP SDK for Node is mature and gives a clean typed API for resources + tools.
Folder structure
.
├── src
│ ├── data
│ │ └── courseData.ts # Static schedule/repo data (edit this each term)
│ ├── tools
│ │ └── courseTools.ts # Pure logic for deadlines, pacing, and routing
│ ├── server.ts # MCP server + tool/resource registration
│ └── index.ts # Stdio entrypoint
├── tests
│ └── courseTools.test.ts # Unit tests for tool logic
├── package.json
├── tsconfig.json
└── vitest.config.ts
Available MCP capabilities
Resource
xcs221://course-data
Full static JSON data for term schedule, assignments, and repositories.
Tools
-
get_assignment_deadlines- Input:
referenceDate?(YYYY-MM-DD)includePast?(boolean)
- Returns assignment due dates from static data.
- Input:
-
get_today_progress- Input:
referenceDate?(YYYY-MM-DD)
- Returns pacing guidance (lecture focus + assignment focus) for that day.
- Input:
-
get_course_repositories- Input: none
- Returns setup and assignment repository URLs.
-
answer_course_question- Input:
question(string)referenceDate?(YYYY-MM-DD)
- Routes natural-language questions to the right static answer set.
- Input:
Quick start
1) Install
npm install
2) Run tests
npm test
3) Start MCP server (stdio transport)
npm run dev
or build + run:
npm run build
npm start
MCP client config example
Use stdio in your MCP client:
{
"mcpServers": {
"xcs221-course-guide": {
"command": "node",
"args": ["/absolute/path/to/repo/dist/index.js"]
}
}
}
If running TypeScript directly in development:
{
"mcpServers": {
"xcs221-course-guide-dev": {
"command": "npx",
"args": ["tsx", "/absolute/path/to/repo/src/index.ts"]
}
}
}
Customizing for your actual course term
Edit src/data/courseData.ts:
- update
term,timezone, andcourseStartDate - replace assignment
dueDateandrepolinks - update
pacingMilestonesdate ranges and topics - update
repositorieslist to your real setup/assignment repos
No auth changes are required unless you intentionally add external systems.
Testing
Current tests cover:
- date validation
- upcoming deadline selection
- day-specific pacing guidance
- natural-language intent routing
- fallback behavior for unknown questions
Add tests in tests/ as you extend new tools or data fields.
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。