braude-mcp

braude-mcp

A serverless MCP server for Ort Braude College that enables AI assistants to query academic calendar dates, search for courses, and retrieve course schedules and classroom assignments.

Category
访问服务器

README

Braude College MCP Server (Cloudflare Worker)

License: MIT Cloudflare Workers Model Context Protocol

A remote, serverless Model Context Protocol (MCP) server for Ort Braude College of Engineering. Built with TypeScript, Hono, and deployed on Cloudflare Workers.

This server enables AI assistants (such as Claude, Codex, Cursor, Windsurf, Gemini Spark, or custom LLM agents) to query real-time academic calendar dates, search for available courses, and look up course schedules and classroom assignments.


⚠️ Legal & Ethical Disclaimer

  • Unofficial Server: This project is an independent, open-source community tool and is NOT affiliated with, authorized, maintained, sponsored, or endorsed by Ort Braude College of Engineering.
  • Robots.txt Compliance: This server strictly respects and adheres to the robots.txt guidelines specified by w3.braude.ac.il and info.braude.ac.il. It only accesses publicly available pages.
  • No Private Data Access: It does NOT access, scrape, or store any private student data, personal accounts, grades, or password-protected portals.
  • Rate Limiting & Server Protection: To ensure zero disruption or overload on the college web infrastructure:
    • Built-in IP Rate Limiting: Enforces a strict limit of 60 requests per minute per IP (returning HTTP 429 Too Many Requests with retry headers when exceeded).
    • In-Memory Caching: Caches scraped public HTML data in memory to minimize outgoing requests to college servers.

🛠️ Features & Available Tools

Tools

Tool Name Description Example Arguments
get_academic_calendar Fetches academic calendar events, semester start/end dates, exam periods, registration dates, and holidays for a given academic year. { "year": "2025-2026" } or {} (defaults to current year)
search_courses Searches the course catalog by keyword, course code, or department name. { "query": "אלגברה ליניארית" } or { "query": "תוכנה", "department": "הנדסת תוכנה" }
get_course_schedule Retrieves detailed schedule options for a course, including lecture/lab groups, days, times, instructors, and classrooms. { "courseCode": "61101" }

Resources

Resource URI MIME Type Description
braude://calendar/current application/json Provides immediate JSON access to the active academic year's calendar events.

🔌 Client Connection Guide

Replace https://braude-mcp.<your-subdomain>.workers.dev/mcp with your deployed Cloudflare Worker URL (or http://127.0.0.1:8787/mcp if running locally).

1. Claude (Claude Desktop & Claude Code CLI)

Claude Desktop App

Edit your claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "braude": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetch",
        "https://braude-mcp.<your-subdomain>.workers.dev/mcp"
      ]
    }
  }
}

Claude Code CLI

Add the remote server via terminal:

claude mcp add braude https://braude-mcp.<your-subdomain>.workers.dev/mcp

2. Codex, Cursor, Windsurf & Antigravity IDEs

In your IDE settings or MCP configuration file (.cursor/mcp.json or .codeium/windsurf/mcp_config.json):

{
  "mcpServers": {
    "braude-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetch",
        "https://braude-mcp.<your-subdomain>.workers.dev/mcp"
      ]
    }
  }
}

3. Gemini Spark & Custom AI Agents

for Gemini Spark go to "Connected Apps", scroll down to "Custome Apps" and click on "Add Custome App" and in there insert the url: https://braude-mcp.<your-subdomain>.workers.dev/mcp and procced with the instructions of gemini.


🚀 Deployment Guide

Prerequisites


Manual Deployment via Wrangler

  1. Install dependencies:

    npm install
    
  2. Authenticate Wrangler:

    npx wrangler login
    
  3. Deploy:

    npm run deploy
    

📦 Uploading the Project to GitHub

To publish this project to GitHub for the first time:

  1. Initialize Git and commit code:

    git init
    git add .
    git commit -m "feat: initial commit for braude-mcp server"
    
  2. Create repository and push to GitHub:

    • Using GitHub CLI (gh):
      gh repo create braude-mcp --public --source=. --remote=origin --push
      
    • Or manually create a repository on GitHub and run:
      git remote add origin https://github.com/YOUR_USERNAME/braude-mcp.git
      git branch -M main
      git push -u origin main
      

🤖 Automated Deployment via GitHub Actions (CI/CD)

This repository includes a GitHub Actions workflow (.github/workflows/deploy.yml) that automatically runs typechecks, runs the unit/integration test suite, and deploys to Cloudflare Workers whenever you push to main or master.

To enable automated deployment, you must add two secret credentials to your GitHub repository settings:

Step 1: Retrieve your CLOUDFLARE_ACCOUNT_ID

  1. Log in to the Cloudflare Dashboard.
  2. Click on Workers & Pages in the left sidebar navigation menu.
  3. On the right side of the page, locate the Account ID field.
  4. Click to copy the 32-character hexadecimal string.

Step 2: Create a CLOUDFLARE_API_TOKEN

  1. In the Cloudflare Dashboard, click your profile icon in the top right corner and select My Profile.
  2. Click API Tokens in the left sidebar menu.
  3. Click the Create Token button.
  4. Locate the Edit Cloudflare Workers template and click Use template.
  5. Ensure the token permissions include:
    • Account | Workers Scripts | Edit
    • Account | Account Settings | Read
  6. Click Continue to summary, then click Create Token.
  7. Copy the generated secret API Token string (Store it securely; Cloudflare will only show it once).

Step 3: Add Secrets to your GitHub Repository

  1. Go to your repository on GitHub: https://github.com/YOUR_USERNAME/braude-mcp.
  2. Click Settings (top tab).
  3. In the left sidebar, expand Secrets and variables and click Actions.
  4. Click New repository secret.
  5. Set Name to CLOUDFLARE_ACCOUNT_ID and Secret to your Account ID string. Click Add secret.
  6. Click New repository secret again.
  7. Set Name to CLOUDFLARE_API_TOKEN and Secret to your API Token string. Click Add secret.

Now, every git push to main will automatically test and deploy your worker!


⚙️ Configuration & Environment Variables

Variable Default Description
ENVIRONMENT production Deployment environment state
RATE_LIMIT_MAX 60 Maximum requests allowed per IP per 1-minute window

To set custom environment variables locally for development, copy .env.example to .dev.vars:

cp .env.example .dev.vars

🧪 Testing & Quality Assurance

Run test suite:

npm test

Run TypeScript typecheck:

npm run typecheck

🏗️ Architecture

               +----------------------------------+
               |   Claude / Codex / Gemini Spark  |
               +----------------------------------+
                                |
                   JSON-RPC 2.0 / HTTP POST
                                v
               +----------------------------------+
               |    Cloudflare Worker (Hono)      |
               |  - Rate Limiter (60 req/min/IP)  |
               |  - CORS & Error Handling         |
               +----------------------------------+
                                |
                                v
               +----------------------------------+
               |        MCP Dispatcher            |
               |  - Tools: calendar & course      |
               |  - Resource: braude://calendar   |
               +----------------------------------+
                                |
                                v
               +----------------------------------+
               |    Scraper Layer & TTL Cache     |
               |  - cheerio DOM Parsing           |
               |  - Respects robots.txt           |
               +----------------------------------+
                                |
               +----------------+----------------+
               |                                 |
               v                                 v
   w3.braude.ac.il (Calendar)       info.braude.ac.il (FireFly)

📄 License

Distributed under the MIT License. See LICENSE for details.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选