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.
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.